Luma Ray 3.2 templates#951
Open
comfyui-wiki wants to merge 4 commits into
Open
Conversation
Created via ComfyUI Template Manager
Updated via ComfyUI Template Manager
📝 WalkthroughWalkthroughTwo new Luma Ray 3.2 video workflow templates ( ChangesLuma Ray 3.2 Video Templates
Sequence DiagramssequenceDiagram
participant User
participant LoadImage
participant LumaRay32ImageToVideoNode
participant LumaRay32ExtendVideoNode
participant SaveVideo
User->>LoadImage: provide cyber_cat.png
LoadImage->>LumaRay32ImageToVideoNode: IMAGE
LumaRay32ImageToVideoNode->>SaveVideo: VIDEO (initial generation)
LumaRay32ImageToVideoNode->>LumaRay32ExtendVideoNode: generation_id as source_generation_id
LumaRay32ExtendVideoNode->>SaveVideo: VIDEO (extended generation)
🚥 Pre-merge checks | ✅ 2✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
✨ Simplify code
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Contributor
🔤 Spellcheck Results
❌ Workflow notes errors
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 9
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (6)
templates/index.ar.json (1)
8849-8871:⚠️ Potential issue | 🟠 Major | ⚡ Quick winFix stale
io.inputsmetadata forapi_runway_aleph2_video_edit.Line 8858 still keeps a
LoadVideoinput (and Line 8852 keeps another stale image input), so this entry now advertises three inputs instead of the intended corrected contract. That makes the catalog metadata sing off-key and can force wrong upload requirements.Proposed fix
"io": { "inputs": [ - { - "nodeId": 3, - "nodeType": "LoadImage", - "file": "example.png", - "mediaType": "image" - }, - { - "nodeId": 4, - "nodeType": "LoadVideo", - "file": "sunset_city_skateboarder.mp4", - "mediaType": "video" - }, { "nodeId": 6, "nodeType": "LoadImage", "file": "example.png", "mediaType": "image" } ], "outputs": [] },🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@templates/index.ar.json` around lines 8849 - 8871, The io.inputs array in the api_runway_aleph2_video_edit metadata contains stale entries that don't match the intended corrected contract. Remove the LoadVideo input with nodeId 4 (line 8858) and the duplicate LoadImage input with nodeId 6 (line 8852) from the inputs array. Keep only the necessary input entries so the metadata accurately reflects the actual input requirements and prevents incorrect upload requirements for users.templates/index.es.json (1)
8858-8871:⚠️ Potential issue | 🟠 Major | ⚡ Quick win
api_runway_aleph2_video_editIO metadata still includesLoadVideo, breaking stated contract.Line 8858-8861 still defines a
LoadVideoinput, which conflicts with the declared update that this entry should keep onlyLoadImageinputs (whileoutputsis empty). One sour note can spoil the whole catalog harmony across locales.💡 Proposed fix
"io": { "inputs": [ { "nodeId": 3, "nodeType": "LoadImage", "file": "example.png", "mediaType": "image" - }, - { - "nodeId": 4, - "nodeType": "LoadVideo", - "file": "sunset_city_skateboarder.mp4", - "mediaType": "video" }, { "nodeId": 6, "nodeType": "LoadImage", "file": "example.png", "mediaType": "image" } ], "outputs": [] },🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@templates/index.es.json` around lines 8858 - 8871, The api_runway_aleph2_video_edit entry in the inputs array contains a LoadVideo node with nodeId 4 that violates the API contract which should only include LoadImage inputs. Remove the entire LoadVideo node object (the one with nodeId 4, nodeType "LoadVideo", and file "sunset_city_skateboarder.mp4") from the inputs array, keeping only the LoadImage node with nodeId 6 that references example.png.templates/index.fa.json (1)
8849-8871:⚠️ Potential issue | 🔴 CriticalUnsupported locale in template index—Persian (fa) is not in the supported language list.
templates/index.fa.jsondoesn't align with the coding guidelines, which explicitly support only 11 locales: en, zh, zh-TW, ja, ko, es, fr, ru, tr, ar, pt-BR. Adding a Persian index is a step in the wrong direction—looks like this template got a little too far-sian from spec! Either remove this file or update the language support guidelines to officially include Persian (fa).🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@templates/index.fa.json` around lines 8849 - 8871, The file templates/index.fa.json contains a template index for Persian locale, but Persian (fa) is not included in the list of officially supported locales which only includes en, zh, zh-TW, ja, ko, es, fr, ru, tr, ar, and pt-BR. Remove the templates/index.fa.json file entirely to align with the coding guidelines, unless Persian language support is being officially added to the project in which case the supported language list documentation should be updated to include fa.templates/index.ja.json (1)
8850-8870:⚠️ Potential issue | 🟠 Major | ⚡ Quick winFix
api_runway_aleph2_video_editIO metadata drift (double image + stray video input).This entry currently defines two identical
LoadImageinputs and still keeps aLoadVideoinput, which conflicts with the intended corrected IO shape (LoadImageonly, empty outputs). A tiny metadata drift now, a bigger UI headache later—rhyme intended.💡 Proposed fix
"io": { "inputs": [ { "nodeId": 3, "nodeType": "LoadImage", "file": "example.png", "mediaType": "image" - }, - { - "nodeId": 4, - "nodeType": "LoadVideo", - "file": "sunset_city_skateboarder.mp4", - "mediaType": "video" - }, - { - "nodeId": 6, - "nodeType": "LoadImage", - "file": "example.png", - "mediaType": "image" } ], "outputs": [] },🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@templates/index.ja.json` around lines 8850 - 8870, In the api_runway_aleph2_video_edit template entry, the inputs array contains duplicate LoadImage nodes (nodeId 3 and nodeId 6 both loading example.png) and an extraneous LoadVideo node (nodeId 4). Correct this by removing one of the duplicate LoadImage entries and deleting the entire LoadVideo input node, leaving only a single LoadImage input in the array while keeping outputs empty.templates/index.pt-BR.json (1)
8858-8871:⚠️ Potential issue | 🟠 Major | ⚡ Quick winFix
api_runway_aleph2_video_editinput contract: extra inputs still present.This entry still includes
LoadVideoand an additionalLoadImage, while the intended update is anio.inputslist containing onlyLoadImage(withio.outputsempty). Right now the metadata is marching to the wrong beat.🛠️ Proposed fix
"io": { "inputs": [ { "nodeId": 3, "nodeType": "LoadImage", "file": "example.png", "mediaType": "image" - }, - { - "nodeId": 4, - "nodeType": "LoadVideo", - "file": "sunset_city_skateboarder.mp4", - "mediaType": "video" - }, - { - "nodeId": 6, - "nodeType": "LoadImage", - "file": "example.png", - "mediaType": "image" } ], "outputs": [] },🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@templates/index.pt-BR.json` around lines 8858 - 8871, The api_runway_aleph2_video_edit entry in the inputs array contains both a LoadVideo node and a LoadImage node, but according to the specification it should only contain the LoadImage node. Remove the entire LoadVideo node object (the one with nodeId 4 and nodeType LoadVideo for the sunset_city_skateboarder.mp4 file) from the inputs array, keeping only the LoadImage node with nodeId 6 that references example.png. Ensure that the outputs array remains empty as intended.templates/index.zh-TW.json (1)
8858-8862:⚠️ Potential issue | 🟠 Major | ⚡ Quick winKeep
api_runway_aleph2_video_editinputs image-only to match the intended metadata contract.
io.inputsstill includesLoadVideoat Line 8859, so this entry is not aligned with the intended correction (inputsonlyLoadImage,outputsempty). A tiny mismatch, big itch.Proposed fix
"io": { "inputs": [ { "nodeId": 3, "nodeType": "LoadImage", "file": "example.png", "mediaType": "image" }, - { - "nodeId": 4, - "nodeType": "LoadVideo", - "file": "sunset_city_skateboarder.mp4", - "mediaType": "video" - }, { "nodeId": 6, "nodeType": "LoadImage", "file": "example.png", "mediaType": "image" } ], "outputs": [] },Also applies to: 8869-8871
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@templates/index.zh-TW.json` around lines 8858 - 8862, Remove the LoadVideo node entry from the io.inputs section of the api_runway_aleph2_video_edit template definition, as the intended metadata contract specifies that inputs should only contain LoadImage nodes. The LoadVideo node at line 8859 with nodeType "LoadVideo" and file "sunset_city_skateboarder.mp4" should be deleted entirely. Additionally, check lines 8869-8871 for similar LoadVideo entries in the inputs and remove those as well to maintain consistency across the template.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@templates/api_luma_ray3_3_t2i.json`:
- Around line 1-288: The workflow template JSON is missing the required
properties.models[] metadata block at the top level. Add a properties object (if
not already present at the root level) with a models array that contains model
metadata entries. Each model entry must include the download URL, SHA256 hash
for integrity verification, and ensure the thumbnail is referenced using the
naming convention api_luma_ray3_3_t2i-1.webp. Place this properties.models[]
block at the top level of the JSON structure alongside existing fields like id,
revision, nodes, links, groups, config, extra, and version.
In `@templates/index.es.json`:
- Around line 8814-8815: The title and description fields for the Luma Ray 3.2
template in the Spanish locale file (templates/index.es.json) are currently in
English instead of Spanish. Translate both the title "Luma Ray 3.2: Text to
Video" and the description about generating cinematic-quality videos into
Spanish to maintain locale consistency across all supported languages. Ensure
the translations are accurate and maintain the marketing intent of the original
English strings.
In `@templates/index.fa.json`:
- Around line 8814-8815: The title "Luma Ray 3.2: Text to Video" and its
description in the index.fa.json file are written in English but should be in
Persian to maintain consistency with this locale file. Translate both the title
and description fields for this catalog entry from English to Persian, ensuring
the translated copy accurately conveys the meaning and maintains the marketing
tone of the original entry.
In `@templates/index.fr.json`:
- Around line 8814-8815: The `title` and `description` fields for the Luma Ray
3.2 entry in the French language template index file (`index.fr.json`) are
currently in English instead of French. Translate these two fields from English
to French to ensure the French catalog maintains consistent language
localization. The `title` field should contain the French translation of "Luma
Ray 3.2: Text to Video" and the `description` field should contain the French
translation of the video generation feature description, maintaining the
original meaning and context.
In `@templates/index.json`:
- Around line 8813-8815: Verify whether the upstream Luma Ray 3.2 model
documentation or API uses the suffix "t2i" for this text-to-video workflow. If
the upstream model actually uses "t2v" (text-to-video) instead, rename the
template from "api_luma_ray3_3_t2i" to "api_luma_ray3_3_t2v" in the
templates/index.json file and update all references consistently across all
locale index files (index.*.json), bundles.json, and i18n.json to ensure the
naming accurately reflects the model's video generation capability and removes
the text-to-image semantics confusion.
In `@templates/index.pt-BR.json`:
- Around line 8814-8815: The "title" and "description" fields for the Luma Ray
3.2 entry in the pt-BR locale file are still in English instead of Portuguese
Brazilian. Translate both the title "Luma Ray 3.2: Text to Video" and the
description text about generating cinematic-quality videos to Portuguese
Brazilian language to maintain consistency with the locale file's intended
language.
In `@templates/index.ru.json`:
- Around line 8814-8815: The Luma Ray 3.2 template entry in the Russian locale
file has English title and description fields that need to be translated to
Russian to maintain consistency with the Russian locale. Locate the "Luma Ray
3.2: Text to Video" template entry and translate both the title field (currently
"Luma Ray 3.2: Text to Video") and the description field (starting with
"Generate cinematic-quality videos") into Russian to ensure the entire locale
file is in Russian and provides a consistent user experience for
Russian-speaking users.
- Around line 8863-8871: The api_runway_aleph2_video_edit template has
conflicting input node definitions with multiple LoadImage nodes and a LoadVideo
node, causing ambiguous io.inputs contract. Review the template and remove the
redundant input node definitions (either remove the newly added LoadImage with
nodeId 6 or clean up the old input nodes) to ensure only a single, clear input
contract remains. Align all input metadata so the template has one consistent
"gate" for inputs matching its actual intended functionality, whether that is
video or image loading.
In `@templates/index.zh.json`:
- Around line 8814-8815: The Luma Ray 3.2 template entry in
templates/index.zh.json file contains English strings in both the "title" and
"description" fields when they should be translated to Chinese for locale
consistency. Translate both the title "Luma Ray 3.2: Text to Video" and the full
description text into Chinese to maintain zh locale consistency and ensure
proper user-facing readability as required by the localization guidelines for
the 11 supported languages.
---
Outside diff comments:
In `@templates/index.ar.json`:
- Around line 8849-8871: The io.inputs array in the api_runway_aleph2_video_edit
metadata contains stale entries that don't match the intended corrected
contract. Remove the LoadVideo input with nodeId 4 (line 8858) and the duplicate
LoadImage input with nodeId 6 (line 8852) from the inputs array. Keep only the
necessary input entries so the metadata accurately reflects the actual input
requirements and prevents incorrect upload requirements for users.
In `@templates/index.es.json`:
- Around line 8858-8871: The api_runway_aleph2_video_edit entry in the inputs
array contains a LoadVideo node with nodeId 4 that violates the API contract
which should only include LoadImage inputs. Remove the entire LoadVideo node
object (the one with nodeId 4, nodeType "LoadVideo", and file
"sunset_city_skateboarder.mp4") from the inputs array, keeping only the
LoadImage node with nodeId 6 that references example.png.
In `@templates/index.fa.json`:
- Around line 8849-8871: The file templates/index.fa.json contains a template
index for Persian locale, but Persian (fa) is not included in the list of
officially supported locales which only includes en, zh, zh-TW, ja, ko, es, fr,
ru, tr, ar, and pt-BR. Remove the templates/index.fa.json file entirely to align
with the coding guidelines, unless Persian language support is being officially
added to the project in which case the supported language list documentation
should be updated to include fa.
In `@templates/index.ja.json`:
- Around line 8850-8870: In the api_runway_aleph2_video_edit template entry, the
inputs array contains duplicate LoadImage nodes (nodeId 3 and nodeId 6 both
loading example.png) and an extraneous LoadVideo node (nodeId 4). Correct this
by removing one of the duplicate LoadImage entries and deleting the entire
LoadVideo input node, leaving only a single LoadImage input in the array while
keeping outputs empty.
In `@templates/index.pt-BR.json`:
- Around line 8858-8871: The api_runway_aleph2_video_edit entry in the inputs
array contains both a LoadVideo node and a LoadImage node, but according to the
specification it should only contain the LoadImage node. Remove the entire
LoadVideo node object (the one with nodeId 4 and nodeType LoadVideo for the
sunset_city_skateboarder.mp4 file) from the inputs array, keeping only the
LoadImage node with nodeId 6 that references example.png. Ensure that the
outputs array remains empty as intended.
In `@templates/index.zh-TW.json`:
- Around line 8858-8862: Remove the LoadVideo node entry from the io.inputs
section of the api_runway_aleph2_video_edit template definition, as the intended
metadata contract specifies that inputs should only contain LoadImage nodes. The
LoadVideo node at line 8859 with nodeType "LoadVideo" and file
"sunset_city_skateboarder.mp4" should be deleted entirely. Additionally, check
lines 8869-8871 for similar LoadVideo entries in the inputs and remove those as
well to maintain consistency across the template.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: bda6a7e0-f2cd-4c7f-8a1e-5c4311b58155
📒 Files selected for processing (16)
bundles.jsonscripts/i18n.jsontemplates/api_luma_ray3_3_t2i-1.webptemplates/api_luma_ray3_3_t2i.jsontemplates/index.ar.jsontemplates/index.es.jsontemplates/index.fa.jsontemplates/index.fr.jsontemplates/index.ja.jsontemplates/index.jsontemplates/index.ko.jsontemplates/index.pt-BR.jsontemplates/index.ru.jsontemplates/index.tr.jsontemplates/index.zh-TW.jsontemplates/index.zh.json
Comment on lines
+1
to
+288
| "properties": { | ||
| "Node name for S&R": "PreviewAny" | ||
| }, | ||
| "widgets_values": [ | ||
| null, | ||
| null, | ||
| null | ||
| ] | ||
| }, | ||
| { | ||
| "id": 9, | ||
| "type": "SaveVideo", | ||
| "pos": [ | ||
| 2820, | ||
| 370 | ||
| ], | ||
| "size": [ | ||
| 450, | ||
| 320 | ||
| ], | ||
| "flags": {}, | ||
| "order": 5, | ||
| "mode": 4, | ||
| "inputs": [ | ||
| { | ||
| "name": "video", | ||
| "type": "VIDEO", | ||
| "link": 5 | ||
| } | ||
| ], | ||
| "outputs": [], | ||
| "properties": {}, | ||
| "widgets_values": [ | ||
| "video/Luma_Ray_3.2_T2V", | ||
| "auto", | ||
| "auto" | ||
| ] | ||
| } | ||
| ], | ||
| "links": [ | ||
| [ | ||
| 2, | ||
| 3, | ||
| 1, | ||
| 4, | ||
| 0, | ||
| "STRING" | ||
| ], | ||
| [ | ||
| 3, | ||
| 3, | ||
| 0, | ||
| 6, | ||
| 0, | ||
| "VIDEO" | ||
| ], | ||
| [ | ||
| 4, | ||
| 3, | ||
| 1, | ||
| 8, | ||
| 0, | ||
| "STRING" | ||
| ], | ||
| [ | ||
| 5, | ||
| 4, | ||
| 0, | ||
| 9, | ||
| 0, | ||
| "VIDEO" | ||
| ] | ||
| ], | ||
| "groups": [ | ||
| { | ||
| "id": 1, | ||
| "title": "Select and Ctrl-B to enable", | ||
| "bounding": [ | ||
| 2380, | ||
| 300, | ||
| 1240, | ||
| 750 | ||
| ], | ||
| "color": "#3f789e", | ||
| "flags": {} | ||
| } | ||
| ], | ||
| "config": {}, | ||
| "extra": { | ||
| "ds": { | ||
| "scale": 0.2834565837654233, | ||
| "offset": [ | ||
| 486.80166711356514, | ||
| 1021.7089900980933 | ||
| ] | ||
| }, | ||
| "frontendVersion": "1.47.2" | ||
| }, | ||
| "version": 0.4 | ||
| } |
There was a problem hiding this comment.
Missing required properties.models[] metadata (no hash, no stash).
This workflow JSON does not include the required embedded model metadata block (properties.models[]) with model download URL(s), SHA256 hash(es), and thumbnail naming (api_luma_ray3_3_t2i-1.webp). Please add it at the top level so template ingestion and integrity checks can rely on canonical metadata.
As per coding guidelines, “Workflow JSON files must follow standard ComfyUI workflow format with embedded model metadata in properties.models[] including download URLs and SHA256 hashes” and “JSON workflow template files should contain embedded model metadata with thumbnails named {template}-1.webp.”
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@templates/api_luma_ray3_3_t2i.json` around lines 1 - 288, The workflow
template JSON is missing the required properties.models[] metadata block at the
top level. Add a properties object (if not already present at the root level)
with a models array that contains model metadata entries. Each model entry must
include the download URL, SHA256 hash for integrity verification, and ensure the
thumbnail is referenced using the naming convention api_luma_ray3_3_t2i-1.webp.
Place this properties.models[] block at the top level of the JSON structure
alongside existing fields like id, revision, nodes, links, groups, config,
extra, and version.
Source: Coding guidelines
Comment on lines
+8814
to
+8815
| "title": "Luma Ray 3.2: Text to Video", | ||
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with optional video extension by providing a generation ID from a previous run. Ideal for creating short film sequences, marketing content, and iterative video refinement.", |
There was a problem hiding this comment.
Localize Spanish catalog strings in the Spanish index.
On Line 8814 and Line 8815, title and description are in English inside templates/index.es.json; this one got “lost in translation.” Please localize them to Spanish to keep locale UX consistent.
💡 Proposed fix
- "title": "Luma Ray 3.2: Text to Video",
- "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with optional video extension by providing a generation ID from a previous run. Ideal for creating short film sequences, marketing content, and iterative video refinement.",
+ "title": "Luma Ray 3.2: Texto a Video",
+ "description": "Genera videos de calidad cinematográfica a partir de prompts de texto con Luma Ray 3.2, con extensión opcional de video al proporcionar un ID de generación de una ejecución anterior. Ideal para crear secuencias cortas, contenido de marketing y refinamiento iterativo de video.",As per coding guidelines, “Support 11 languages in templates: en (default), zh, zh-TW, ja, ko, es, fr, ru, tr, ar, pt-BR; maintain corresponding index.{locale}.json files for each locale”.
📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| "title": "Luma Ray 3.2: Text to Video", | |
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with optional video extension by providing a generation ID from a previous run. Ideal for creating short film sequences, marketing content, and iterative video refinement.", | |
| "title": "Luma Ray 3.2: Texto a Video", | |
| "description": "Genera videos de calidad cinematográfica a partir de prompts de texto con Luma Ray 3.2, con extensión opcional de video al proporcionar un ID de generación de una ejecución anterior. Ideal para crear secuencias cortas, contenido de marketing y refinamiento iterativo de video.", |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@templates/index.es.json` around lines 8814 - 8815, The title and description
fields for the Luma Ray 3.2 template in the Spanish locale file
(templates/index.es.json) are currently in English instead of Spanish. Translate
both the title "Luma Ray 3.2: Text to Video" and the description about
generating cinematic-quality videos into Spanish to maintain locale consistency
across all supported languages. Ensure the translations are accurate and
maintain the marketing intent of the original English strings.
Source: Coding guidelines
Comment on lines
+8814
to
+8815
| "title": "Luma Ray 3.2: Text to Video", | ||
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with optional video extension by providing a generation ID from a previous run. Ideal for creating short film sequences, marketing content, and iterative video refinement.", |
There was a problem hiding this comment.
Localize the new Persian catalog copy for a consistent UX.
The new entry’s title and description are English in index.fa.json; a locale in time saves nine. Please provide Persian copy to match this catalog’s language.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@templates/index.fa.json` around lines 8814 - 8815, The title "Luma Ray 3.2:
Text to Video" and its description in the index.fa.json file are written in
English but should be in Persian to maintain consistency with this locale file.
Translate both the title and description fields for this catalog entry from
English to Persian, ensuring the translated copy accurately conveys the meaning
and maintains the marketing tone of the original entry.
Comment on lines
+8814
to
+8815
| "title": "Luma Ray 3.2: Text to Video", | ||
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with optional video extension by providing a generation ID from a previous run. Ideal for creating short film sequences, marketing content, and iterative video refinement.", |
There was a problem hiding this comment.
Localize the new template strings in the French index.
title and description are in English inside templates/index.fr.json, so the FR catalog becomes mixed-language (a tiny Babel bug with a big UX shrug).
As per coding guidelines, "Support 11 languages in templates: en (default), zh, zh-TW, ja, ko, es, fr, ru, tr, ar, pt-BR; maintain corresponding index.{locale}.json files for each locale."
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@templates/index.fr.json` around lines 8814 - 8815, The `title` and
`description` fields for the Luma Ray 3.2 entry in the French language template
index file (`index.fr.json`) are currently in English instead of French.
Translate these two fields from English to French to ensure the French catalog
maintains consistent language localization. The `title` field should contain the
French translation of "Luma Ray 3.2: Text to Video" and the `description` field
should contain the French translation of the video generation feature
description, maintaining the original meaning and context.
Source: Coding guidelines
Comment on lines
+8814
to
+8815
| "title": "Luma Ray 3.2: Text to Video", | ||
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with optional video extension by providing a generation ID from a previous run. Ideal for creating short film sequences, marketing content, and iterative video refinement.", |
There was a problem hiding this comment.
Localize the new pt-BR strings (this one’s out of locale, out of tune).
Line 8814 and Line 8815 are English in a pt-BR index file; this creates a visible language mismatch in catalog UI.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@templates/index.pt-BR.json` around lines 8814 - 8815, The "title" and
"description" fields for the Luma Ray 3.2 entry in the pt-BR locale file are
still in English instead of Portuguese Brazilian. Translate both the title "Luma
Ray 3.2: Text to Video" and the description text about generating
cinematic-quality videos to Portuguese Brazilian language to maintain
consistency with the locale file's intended language.
Comment on lines
+8814
to
+8815
| "title": "Luma Ray 3.2: Text to Video", | ||
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with optional video extension by providing a generation ID from a previous run. Ideal for creating short film sequences, marketing content, and iterative video refinement.", |
There was a problem hiding this comment.
Локаль ru отклонилась на английский — стоит перевести title/description.
В templates/index.ru.json новый шаблон добавлен с англоязычными строками; это выбивается из русской витрины и ухудшает UX локали.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@templates/index.ru.json` around lines 8814 - 8815, The Luma Ray 3.2 template
entry in the Russian locale file has English title and description fields that
need to be translated to Russian to maintain consistency with the Russian
locale. Locate the "Luma Ray 3.2: Text to Video" template entry and translate
both the title field (currently "Luma Ray 3.2: Text to Video") and the
description field (starting with "Generate cinematic-quality videos") into
Russian to ensure the entire locale file is in Russian and provides a consistent
user experience for Russian-speaking users.
Comment on lines
+8863
to
+8871
| { | ||
| "nodeId": 6, | ||
| "nodeType": "LoadImage", | ||
| "file": "example.png", | ||
| "mediaType": "image" | ||
| } | ||
| ] | ||
| } | ||
| ], | ||
| "outputs": [] | ||
| }, |
There was a problem hiding this comment.
api_runway_aleph2_video_edit получил двусмысленный io.inputs контракт (два LoadImage + LoadVideo).
После правки в этой локали у шаблона остались старые входы и добавился новый LoadImage (nodeId 6), из-за чего метаданные ввода выглядят конфликтно и могут неверно формировать UI-входы. Коротко: один шаблон — слишком много “врат”, и ритм ломается как бит без такта.
Proposed fix (align IO metadata to a single intended input contract)
"io": {
"inputs": [
- {
- "nodeId": 3,
- "nodeType": "LoadImage",
- "file": "example.png",
- "mediaType": "image"
- },
- {
- "nodeId": 4,
- "nodeType": "LoadVideo",
- "file": "sunset_city_skateboarder.mp4",
- "mediaType": "video"
- },
{
"nodeId": 6,
"nodeType": "LoadImage",
"file": "example.png",
"mediaType": "image"
}
],
"outputs": []
},🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@templates/index.ru.json` around lines 8863 - 8871, The
api_runway_aleph2_video_edit template has conflicting input node definitions
with multiple LoadImage nodes and a LoadVideo node, causing ambiguous io.inputs
contract. Review the template and remove the redundant input node definitions
(either remove the newly added LoadImage with nodeId 6 or clean up the old input
nodes) to ensure only a single, clear input contract remains. Align all input
metadata so the template has one consistent "gate" for inputs matching its
actual intended functionality, whether that is video or image loading.
Comment on lines
+8814
to
+8815
| "title": "Luma Ray 3.2: Text to Video", | ||
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with optional video extension by providing a generation ID from a previous run. Ideal for creating short film sequences, marketing content, and iterative video refinement.", |
There was a problem hiding this comment.
Localize the zh catalog text for the new template entry.
Line 8814 and Line 8815 are English strings in templates/index.zh.json; this breaks zh locale consistency and user-facing readability (a tiny locale pothole with a big UI toll).
As per coding guidelines, “Support 11 languages in templates: en (default), zh, zh-TW, ja, ko, es, fr, ru, tr, ar, pt-BR; maintain corresponding index.{locale}.json files for each locale”.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@templates/index.zh.json` around lines 8814 - 8815, The Luma Ray 3.2 template
entry in templates/index.zh.json file contains English strings in both the
"title" and "description" fields when they should be translated to Chinese for
locale consistency. Translate both the title "Luma Ray 3.2: Text to Video" and
the full description text into Chinese to maintain zh locale consistency and
ensure proper user-facing readability as required by the localization guidelines
for the 11 supported languages.
Source: Coding guidelines
Created via ComfyUI Template Manager
There was a problem hiding this comment.
Actionable comments posted: 14
♻️ Duplicate comments (3)
templates/index.fa.json (1)
8815-8815:⚠️ Potential issue | 🟡 Minor | ⚡ Quick win
i2vdescription currently reads liket2v(identity crisis alert).At Line 8815, the copy says “from text prompts” for
api_luma_ray3_3_i2v, which conflicts with image-to-video behavior and can mislead users.Suggested copy fix
- "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", + "description": "Generate cinematic-quality videos from input images using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.",🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@templates/index.fa.json` at line 8815, The description for the api_luma_ray3_3_i2v template is incorrectly describing text-to-video behavior instead of image-to-video behavior. Locate the description field for api_luma_ray3_3_i2v and replace the phrase "from text prompts" with language that accurately reflects image-to-video functionality, such as "from images" or "from image inputs". Ensure the description clearly conveys that this endpoint accepts images as input to generate videos, not text prompts.templates/index.pt-BR.json (1)
8814-8815:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winLocalize and correct the
api_luma_ray3_3_i2vcopy in pt-BR (this locale rhyme is out of time).Line 8814–Line 8815 are still in English, and the description says “from text prompts” for an
i2vtemplate. Please translate to pt-BR and align wording to image-to-video behavior.💡 Suggested patch
- "title": "Luma Ray 3.2: Image to Video", - "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", + "title": "Luma Ray 3.2: Imagem para Vídeo", + "description": "Gere vídeos de qualidade cinematográfica a partir de imagens usando o Luma Ray 3.2, com suporte para estender gerações anteriores ao informar um generation ID. O fluxo de trabalho aceita 1 imagem de entrada e produz 1 saída de vídeo, permitindo refinamento iterativo contínuo. Ideal para criar sequências curtas de filme, conteúdo de marketing e produção de vídeo profissional.",As per coding guidelines, “Support 11 languages in templates: en (default), zh, zh-TW, ja, ko, es, fr, ru, tr, ar, pt-BR; maintain corresponding
index.{locale}.jsonfiles for each locale”.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@templates/index.pt-BR.json` around lines 8814 - 8815, In the Portuguese-Brazilian locale file (index.pt-BR.json), locate the api_luma_ray3_3_i2v template entry around lines 8814-8815 with the title "Luma Ray 3.2: Image to Video". Translate both the title and description to Portuguese-Brazilian language. Additionally, correct the description text which currently states "from text prompts" to accurately reflect image-to-video behavior by saying it generates from image inputs instead, while preserving all other details about cinematic quality, generation extension capabilities, and use cases for short films and marketing content.Source: Coding guidelines
templates/index.zh.json (1)
8814-8815:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winUnlocalized zh catalog text is still present.
Line 8814 and Line 8815 are still English in
templates/index.zh.json; this breaks locale consistency for zh users.As per coding guidelines, “Support 11 languages in templates: en (default), zh, zh-TW, ja, ko, es, fr, ru, tr, ar, pt-BR; maintain corresponding
index.{locale}.jsonfiles for each locale”.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@templates/index.zh.json` around lines 8814 - 8815, The "title" and "description" fields for the Luma Ray 3.2 entry in the templates/index.zh.json file are still in English instead of being translated to Simplified Chinese. Translate both the "title" value "Luma Ray 3.2: Image to Video" and the entire "description" value from English to Simplified Chinese to maintain locale consistency for zh users, following the requirement to support localized catalog text for all 11 supported languages.Source: Coding guidelines
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@scripts/i18n.json`:
- Around line 4728-4746: The missing_languages array for the api_luma_ray3_3_i2v
entry contains "fa" (Farsi), which is not one of the 11 supported languages
defined in the coding guidelines (en, zh, zh-TW, ja, ko, es, fr, ru, tr, ar,
pt-BR). Remove "fa" from the missing_languages array in the api_luma_ray3_3_i2v
object to align with the supported language scope.
- Around line 21293-21304: The description text for the image-to-video template
incorrectly describes the input as "from text prompts" which is copy-pasted from
the text-to-video template. Update all language entries (en, zh, zh-TW, ja, ko,
es, fr, ru, tr, ar, pt-BR, fa) in this section by replacing "from text prompts"
with appropriate language that accurately reflects the template accepts input
images, not text prompts. Ensure the corrected description emphasizes that the
workflow takes an input image and generates video from it.
In `@templates/api_luma_ray3_3_i2v.json`:
- Line 146: The video path prefix in the I2V template incorrectly uses "T2V"
(Text-to-Video) instead of "I2V" (Image-to-Video), which causes inconsistent
output organization between template types. Change the string
"video/Luma_Ray_3.2_T2V" to use the "I2V" suffix instead of "T2V" to properly
reflect the template's purpose and maintain consistent output directory
structure.
- Around line 1-344: The template file is missing required embedded model
metadata in the root-level properties object. Add a models array to the
properties field containing entries with download URLs and SHA256 hashes for
each model used by the LumaRay32ImageToVideoNode and LumaRay32ExtendVideoNode
nodes. Additionally, create and add a thumbnail image file named
api_luma_ray3_3_i2v-1.webp in the templates directory that visually represents
this workflow template to comply with the repository's template contract
requirements.
In `@templates/index.ar.json`:
- Line 8815: The description for the api_luma_ray3_3_i2v template entry is
incorrectly describing text-to-video behavior by mentioning "from text prompts,"
when this is an image-to-video template. Update the description field to
accurately reflect image-to-video functionality by removing the reference to
text prompts and instead focusing on how the template generates videos from
input images, making it clear this is an image-to-video tool rather than
text-to-video.
In `@templates/index.es.json`:
- Around line 8813-8815: The description for the api_luma_ray3_3_i2v template
incorrectly states that it generates videos "from text prompts" when this is an
image-to-video template. Update the description field to remove the reference to
text prompts and instead accurately describe the workflow as generating videos
from input images, maintaining consistency with the template name (i2v =
image-to-video) and title.
In `@templates/index.fr.json`:
- Line 8815: The description on line 8815 for the i2v (image-to-video) template
incorrectly states "Generate cinematic-quality videos from text prompts" which
describes t2v (text-to-video) functionality instead. Update the description to
accurately reflect that this template generates videos from images, removing the
reference to "text prompts" and clarifying that it accepts an input image to
produce video output through image-to-video generation.
In `@templates/index.ja.json`:
- Line 8815: The description for the api_luma_ray3_3_i2v template incorrectly
states that videos are generated from text prompts, but this is an
image-to-video template. Update the description to accurately reflect that it
accepts an image as input and generates videos from that image, not from text
prompts. Ensure the description clearly indicates the input is an image and the
template is for image-to-video generation, not text-to-video generation.
In `@templates/index.json`:
- Line 8815: The description for the api_luma_ray3_3_i2v template incorrectly
states that videos are generated "from text prompts," but this is an
Image-to-Video workflow that should generate videos from images. Update the
description text at line 8815 to accurately reflect that this template generates
cinematic-quality videos from input images rather than from text prompts,
ensuring the description aligns with the i2v (image-to-video) functionality of
the api_luma_ray3_3_i2v template.
In `@templates/index.ko.json`:
- Line 8815: The description for the api_luma_ray3_3_i2v template entry
incorrectly describes the template as generating videos "from text prompts,"
which contradicts the image-to-video (i2v) nature of the template. Update the
description field to accurately reflect that this is an image-to-video
conversion template, emphasizing that it accepts images as primary input and
converts them to videos, rather than generating from text prompts. Ensure the
description clearly conveys the image-to-video workflow to guide users to the
correct template for their use case.
In `@templates/index.ru.json`:
- Around line 8814-8815: The title and description fields for the
api_luma_ray3_3_i2v catalog entry in index.ru.json are written in English
instead of Russian, violating the locale requirement for the .ru.json file.
Additionally, the description incorrectly states "from text prompts" for an
image-to-video template when it should reference generating from images.
Translate both the title "Luma Ray 3.2: Image to Video" and the description to
Russian, and correct the description to accurately reflect that videos are
generated from input images rather than text prompts, ensuring the modality
description matches the i2v template type.
In `@templates/index.tr.json`:
- Around line 8813-8816: The description for the api_luma_ray3_3_i2v template
object incorrectly states it generates videos "from text prompts" when this is
an image-to-video template that accepts image inputs, not text inputs. Update
the description field to remove the reference to text prompts and accurately
describe that the template generates videos from a single input image, ensuring
consistency with the template name (i2v stands for image-to-video) and the
earlier statement about accepting "1 input image".
In `@templates/index.zh-TW.json`:
- Line 8815: The description for the api_luma_ray3_3_i2v template entry
incorrectly states it generates videos "from text prompts" when this is an
image-to-video template that accepts 1 input image. Update the description to
correctly reflect that it generates cinematic-quality videos from image inputs
rather than text prompts, while keeping the rest of the description about
supporting generation extension and iterative refinement relevant to the
image-to-video use case.
In `@templates/index.zh.json`:
- Line 8815: The description for the api_luma_ray3_3_i2v template incorrectly
states that videos are generated "from text prompts" when this is an
image-to-video template, not text-to-video. Update the description text at line
8815 to remove the reference to "text prompts" and replace it with wording that
accurately reflects the image-to-video functionality, making clear that the
input is an image (not text) that gets transformed into video output.
---
Duplicate comments:
In `@templates/index.fa.json`:
- Line 8815: The description for the api_luma_ray3_3_i2v template is incorrectly
describing text-to-video behavior instead of image-to-video behavior. Locate the
description field for api_luma_ray3_3_i2v and replace the phrase "from text
prompts" with language that accurately reflects image-to-video functionality,
such as "from images" or "from image inputs". Ensure the description clearly
conveys that this endpoint accepts images as input to generate videos, not text
prompts.
In `@templates/index.pt-BR.json`:
- Around line 8814-8815: In the Portuguese-Brazilian locale file
(index.pt-BR.json), locate the api_luma_ray3_3_i2v template entry around lines
8814-8815 with the title "Luma Ray 3.2: Image to Video". Translate both the
title and description to Portuguese-Brazilian language. Additionally, correct
the description text which currently states "from text prompts" to accurately
reflect image-to-video behavior by saying it generates from image inputs
instead, while preserving all other details about cinematic quality, generation
extension capabilities, and use cases for short films and marketing content.
In `@templates/index.zh.json`:
- Around line 8814-8815: The "title" and "description" fields for the Luma Ray
3.2 entry in the templates/index.zh.json file are still in English instead of
being translated to Simplified Chinese. Translate both the "title" value "Luma
Ray 3.2: Image to Video" and the entire "description" value from English to
Simplified Chinese to maintain locale consistency for zh users, following the
requirement to support localized catalog text for all 11 supported languages.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 9f08c41b-4cd7-494f-9e27-8e273107ca4a
📒 Files selected for processing (16)
bundles.jsonscripts/i18n.jsontemplates/api_luma_ray3_3_i2v-1.webptemplates/api_luma_ray3_3_i2v.jsontemplates/index.ar.jsontemplates/index.es.jsontemplates/index.fa.jsontemplates/index.fr.jsontemplates/index.ja.jsontemplates/index.jsontemplates/index.ko.jsontemplates/index.pt-BR.jsontemplates/index.ru.jsontemplates/index.tr.jsontemplates/index.zh-TW.jsontemplates/index.zh.json
Comment on lines
+21293
to
+21304
| "en": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", | ||
| "zh": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", | ||
| "zh-TW": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", | ||
| "ja": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", | ||
| "ko": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", | ||
| "es": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", | ||
| "fr": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", | ||
| "ru": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", | ||
| "tr": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", | ||
| "ar": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", | ||
| "pt-BR": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", | ||
| "fa": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production." |
There was a problem hiding this comment.
Description text incorrectly describes image-to-video template as text-to-video.
Line 21293 reads: "Generate cinematic-quality videos from text prompts..." This is copy-pasted from the api_luma_ray3_3_t2i (text-to-video) template. For the image-to-video (api_luma_ray3_3_i2v) template, the description should reference input images, not text prompts. This misrepresents the template's actual functionality—it's a prompt mismatch that could confuse users.
Correct the description to accurately reflect that the template accepts an input image, not text prompts. (You might say the copy-paste is... raster than it seems! 🎬)
✏️ Proposed fix
"description": {
"en": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.",
+ /* CORRECTED: Change to reference input image, not text prompts */
+ "en": "Generate cinematic-quality videos from a single input image using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative video extension and refinement. Ideal for creating short film sequences, marketing content, and professional video production.",
- "zh": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.",
+ "zh": "Generate cinematic-quality videos from a single input image using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative video extension and refinement. Ideal for creating short film sequences, marketing content, and professional video production.",
/* ... repeat for all language keys: zh-TW, ja, ko, es, fr, ru, tr, ar, pt-BR ... */Note: Since this is marked as a missing translation field (with all non-English languages showing the same English text), correcting the English text will automatically affect all language entries until proper translations are provided by the translation team.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@scripts/i18n.json` around lines 21293 - 21304, The description text for the
image-to-video template incorrectly describes the input as "from text prompts"
which is copy-pasted from the text-to-video template. Update all language
entries (en, zh, zh-TW, ja, ko, es, fr, ru, tr, ar, pt-BR, fa) in this section
by replacing "from text prompts" with appropriate language that accurately
reflects the template accepts input images, not text prompts. Ensure the
corrected description emphasizes that the workflow takes an input image and
generates video from it.
Comment on lines
+1
to
+344
| { | ||
| "id": "b277498e-2a80-4514-9bd6-3695ea8c1bbb", | ||
| "revision": 0, | ||
| "last_node_id": 23, | ||
| "last_link_id": 23, | ||
| "nodes": [ | ||
| { | ||
| "id": 4, | ||
| "type": "LumaRay32ExtendVideoNode", | ||
| "pos": [ | ||
| 2430, | ||
| 380 | ||
| ], | ||
| "size": [ | ||
| 400, | ||
| 324 | ||
| ], | ||
| "flags": {}, | ||
| "order": 5, | ||
| "mode": 4, | ||
| "inputs": [ | ||
| { | ||
| "name": "source_generation_id", | ||
| "type": "STRING", | ||
| "widget": { | ||
| "name": "source_generation_id" | ||
| }, | ||
| "link": 23 | ||
| } | ||
| ], | ||
| "outputs": [ | ||
| { | ||
| "name": "VIDEO", | ||
| "type": "VIDEO", | ||
| "links": [ | ||
| 5 | ||
| ] | ||
| }, | ||
| { | ||
| "name": "generation_id", | ||
| "type": "STRING", | ||
| "links": null | ||
| } | ||
| ], | ||
| "properties": { | ||
| "Node name for S&R": "LumaRay32ExtendVideoNode" | ||
| }, | ||
| "widgets_values": [ | ||
| "", | ||
| "Forward (continue after)", | ||
| false, | ||
| "", | ||
| "720p", | ||
| 86776790117141, | ||
| "randomize" | ||
| ], | ||
| "color": "#432", | ||
| "bgcolor": "#653" | ||
| }, | ||
| { | ||
| "id": 7, | ||
| "type": "MarkdownNote", | ||
| "pos": [ | ||
| 2440, | ||
| 780 | ||
| ], | ||
| "size": [ | ||
| 400, | ||
| 240 | ||
| ], | ||
| "flags": {}, | ||
| "order": 0, | ||
| "mode": 0, | ||
| "inputs": [], | ||
| "outputs": [], | ||
| "title": "Note: Extend Video", | ||
| "properties": {}, | ||
| "widgets_values": [ | ||
| "This section is for extending videos; it requires a `generation_id` from the previous *Luma Ray 3.2* node.\n\n1. You can unlink the `source_generation_id` input and use the `id` shown on the `Preview as Text` node\n2. Enable it to extend video by default" | ||
| ], | ||
| "color": "#222", | ||
| "bgcolor": "#000" | ||
| }, | ||
| { | ||
| "id": 8, | ||
| "type": "PreviewAny", | ||
| "pos": [ | ||
| 1780, | ||
| 310 | ||
| ], | ||
| "size": [ | ||
| 530, | ||
| 230 | ||
| ], | ||
| "flags": {}, | ||
| "order": 4, | ||
| "mode": 0, | ||
| "inputs": [ | ||
| { | ||
| "name": "source", | ||
| "type": "*", | ||
| "link": 22 | ||
| } | ||
| ], | ||
| "outputs": [ | ||
| { | ||
| "name": "STRING", | ||
| "type": "STRING", | ||
| "links": null | ||
| } | ||
| ], | ||
| "title": "Preview as Text (generation_id)", | ||
| "properties": { | ||
| "Node name for S&R": "PreviewAny" | ||
| }, | ||
| "widgets_values": [ | ||
| null, | ||
| null, | ||
| null | ||
| ] | ||
| }, | ||
| { | ||
| "id": 9, | ||
| "type": "SaveVideo", | ||
| "pos": [ | ||
| 2870, | ||
| 380 | ||
| ], | ||
| "size": [ | ||
| 450, | ||
| 320 | ||
| ], | ||
| "flags": {}, | ||
| "order": 6, | ||
| "mode": 4, | ||
| "inputs": [ | ||
| { | ||
| "name": "video", | ||
| "type": "VIDEO", | ||
| "link": 5 | ||
| } | ||
| ], | ||
| "outputs": [], | ||
| "properties": {}, | ||
| "widgets_values": [ | ||
| "video/Luma_Ray_3.2_T2V", | ||
| "auto", | ||
| "auto" | ||
| ] | ||
| }, | ||
| { | ||
| "id": 11, | ||
| "type": "LoadImage", | ||
| "pos": [ | ||
| 170, | ||
| 310 | ||
| ], | ||
| "size": [ | ||
| 380, | ||
| 370 | ||
| ], | ||
| "flags": {}, | ||
| "order": 1, | ||
| "mode": 0, | ||
| "inputs": [], | ||
| "outputs": [ | ||
| { | ||
| "name": "IMAGE", | ||
| "type": "IMAGE", | ||
| "links": [ | ||
| 11 | ||
| ] | ||
| }, | ||
| { | ||
| "name": "MASK", | ||
| "type": "MASK", | ||
| "links": null | ||
| } | ||
| ], | ||
| "properties": { | ||
| "Node name for S&R": "LoadImage" | ||
| }, | ||
| "widgets_values": [ | ||
| "cyber_cat.png", | ||
| "image" | ||
| ] | ||
| }, | ||
| { | ||
| "id": 12, | ||
| "type": "SaveVideo", | ||
| "pos": [ | ||
| 1120, | ||
| 310 | ||
| ], | ||
| "size": [ | ||
| 580, | ||
| 770 | ||
| ], | ||
| "flags": {}, | ||
| "order": 3, | ||
| "mode": 0, | ||
| "inputs": [ | ||
| { | ||
| "name": "video", | ||
| "type": "VIDEO", | ||
| "link": 10 | ||
| } | ||
| ], | ||
| "outputs": [], | ||
| "properties": {}, | ||
| "widgets_values": [ | ||
| "video/Luma_Ray_3.2_I2V", | ||
| "auto", | ||
| "auto" | ||
| ] | ||
| }, | ||
| { | ||
| "id": 13, | ||
| "type": "LumaRay32ImageToVideoNode", | ||
| "pos": [ | ||
| 650, | ||
| 310 | ||
| ], | ||
| "size": [ | ||
| 400, | ||
| 320 | ||
| ], | ||
| "flags": {}, | ||
| "order": 2, | ||
| "mode": 0, | ||
| "inputs": [ | ||
| { | ||
| "name": "start_frame", | ||
| "shape": 7, | ||
| "type": "IMAGE", | ||
| "link": 11 | ||
| }, | ||
| { | ||
| "name": "end_frame", | ||
| "shape": 7, | ||
| "type": "IMAGE", | ||
| "link": null | ||
| } | ||
| ], | ||
| "outputs": [ | ||
| { | ||
| "name": "VIDEO", | ||
| "type": "VIDEO", | ||
| "links": [ | ||
| 10 | ||
| ] | ||
| }, | ||
| { | ||
| "name": "generation_id", | ||
| "type": "STRING", | ||
| "links": [ | ||
| 22, | ||
| 23 | ||
| ] | ||
| } | ||
| ], | ||
| "properties": { | ||
| "Node name for S&R": "LumaRay32ImageToVideoNode" | ||
| }, | ||
| "widgets_values": [ | ||
| "Monochrome black and white mechanical robotic sphynx cat, seamless segmented metal skull, countless thick data cables flowing from neck like dreadlocks, glowing narrow vertical white slit eyes, sleek cybernetic feline body built like a cheetah for sprinting, full-body running sprint pose, low tracking parallel camera moves alongside the robot cat to capture dynamic fast running motion, camera slowly pull back wide to reveal the entire streamlined cyber cat body, futuristic cyberpunk city environment, towering neon-lit metallic skyscrapers, glowing circuit billboards, wet reflective asphalt ground with hologram reflections, dense tech wiring infrastructure, industrial sci-fi atmosphere, dramatic cinematic side lighting, high contrast monochrome, hyper detailed mechanical textures, scratch worn metal panels, intricate bolt and gear details, motion blur on paws and cable tails to emphasize speed, 8K ultra realistic, photorealistic, shallow dynamic motion blur, epic sci-fi cinematography, sharp industrial blueprint background subtle overlay texture, no text, no watermark", | ||
| "720p", | ||
| false, | ||
| 569886435760230, | ||
| "randomize" | ||
| ], | ||
| "color": "#432", | ||
| "bgcolor": "#653" | ||
| } | ||
| ], | ||
| "links": [ | ||
| [ | ||
| 5, | ||
| 4, | ||
| 0, | ||
| 9, | ||
| 0, | ||
| "VIDEO" | ||
| ], | ||
| [ | ||
| 10, | ||
| 13, | ||
| 0, | ||
| 12, | ||
| 0, | ||
| "VIDEO" | ||
| ], | ||
| [ | ||
| 11, | ||
| 11, | ||
| 0, | ||
| 13, | ||
| 0, | ||
| "IMAGE" | ||
| ], | ||
| [ | ||
| 22, | ||
| 13, | ||
| 1, | ||
| 8, | ||
| 0, | ||
| "STRING" | ||
| ], | ||
| [ | ||
| 23, | ||
| 13, | ||
| 1, | ||
| 4, | ||
| 0, | ||
| "STRING" | ||
| ] | ||
| ], | ||
| "groups": [ | ||
| { | ||
| "id": 1, | ||
| "title": "Select and Ctrl-B to enable", | ||
| "bounding": [ | ||
| 2380, | ||
| 300, | ||
| 1000, | ||
| 770 | ||
| ], | ||
| "color": "#3f789e", | ||
| "flags": {} | ||
| } | ||
| ], | ||
| "config": {}, | ||
| "extra": { | ||
| "ds": { | ||
| "scale": 0.5424975779423886, | ||
| "offset": [ | ||
| 215.64003577404847, | ||
| 128.38508536243685 | ||
| ] | ||
| }, | ||
| "frontendVersion": "1.47.2" | ||
| }, | ||
| "version": 0.4 | ||
| } No newline at end of file |
There was a problem hiding this comment.
Missing required embedded model metadata (no hash, no splash).
This template is missing required embedded model metadata in properties.models[] (including download URL + SHA256), and it does not define a thumbnail following api_luma_ray3_3_i2v-1.webp. This breaks the repository’s template contract.
Suggested patch shape
{
"id": "b277498e-2a80-4514-9bd6-3695ea8c1bbb",
...
"extra": {
"ds": {
"scale": 0.5424975779423886,
"offset": [
215.64003577404847,
128.38508536243685
]
},
"frontendVersion": "1.47.2"
},
+ "properties": {
+ "models": [
+ {
+ "name": "luma_ray3_3_i2v",
+ "thumbnail": "api_luma_ray3_3_i2v-1.webp",
+ "url": "https://<model-download-url>",
+ "sha256": "<sha256>"
+ }
+ ]
+ },
"version": 0.4
}As per coding guidelines, templates/**/*.json workflow files must include embedded metadata in properties.models[] with download URLs and SHA256, and use thumbnails named {template}-1.webp.
📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| { | |
| "id": "b277498e-2a80-4514-9bd6-3695ea8c1bbb", | |
| "revision": 0, | |
| "last_node_id": 23, | |
| "last_link_id": 23, | |
| "nodes": [ | |
| { | |
| "id": 4, | |
| "type": "LumaRay32ExtendVideoNode", | |
| "pos": [ | |
| 2430, | |
| 380 | |
| ], | |
| "size": [ | |
| 400, | |
| 324 | |
| ], | |
| "flags": {}, | |
| "order": 5, | |
| "mode": 4, | |
| "inputs": [ | |
| { | |
| "name": "source_generation_id", | |
| "type": "STRING", | |
| "widget": { | |
| "name": "source_generation_id" | |
| }, | |
| "link": 23 | |
| } | |
| ], | |
| "outputs": [ | |
| { | |
| "name": "VIDEO", | |
| "type": "VIDEO", | |
| "links": [ | |
| 5 | |
| ] | |
| }, | |
| { | |
| "name": "generation_id", | |
| "type": "STRING", | |
| "links": null | |
| } | |
| ], | |
| "properties": { | |
| "Node name for S&R": "LumaRay32ExtendVideoNode" | |
| }, | |
| "widgets_values": [ | |
| "", | |
| "Forward (continue after)", | |
| false, | |
| "", | |
| "720p", | |
| 86776790117141, | |
| "randomize" | |
| ], | |
| "color": "#432", | |
| "bgcolor": "#653" | |
| }, | |
| { | |
| "id": 7, | |
| "type": "MarkdownNote", | |
| "pos": [ | |
| 2440, | |
| 780 | |
| ], | |
| "size": [ | |
| 400, | |
| 240 | |
| ], | |
| "flags": {}, | |
| "order": 0, | |
| "mode": 0, | |
| "inputs": [], | |
| "outputs": [], | |
| "title": "Note: Extend Video", | |
| "properties": {}, | |
| "widgets_values": [ | |
| "This section is for extending videos; it requires a `generation_id` from the previous *Luma Ray 3.2* node.\n\n1. You can unlink the `source_generation_id` input and use the `id` shown on the `Preview as Text` node\n2. Enable it to extend video by default" | |
| ], | |
| "color": "#222", | |
| "bgcolor": "#000" | |
| }, | |
| { | |
| "id": 8, | |
| "type": "PreviewAny", | |
| "pos": [ | |
| 1780, | |
| 310 | |
| ], | |
| "size": [ | |
| 530, | |
| 230 | |
| ], | |
| "flags": {}, | |
| "order": 4, | |
| "mode": 0, | |
| "inputs": [ | |
| { | |
| "name": "source", | |
| "type": "*", | |
| "link": 22 | |
| } | |
| ], | |
| "outputs": [ | |
| { | |
| "name": "STRING", | |
| "type": "STRING", | |
| "links": null | |
| } | |
| ], | |
| "title": "Preview as Text (generation_id)", | |
| "properties": { | |
| "Node name for S&R": "PreviewAny" | |
| }, | |
| "widgets_values": [ | |
| null, | |
| null, | |
| null | |
| ] | |
| }, | |
| { | |
| "id": 9, | |
| "type": "SaveVideo", | |
| "pos": [ | |
| 2870, | |
| 380 | |
| ], | |
| "size": [ | |
| 450, | |
| 320 | |
| ], | |
| "flags": {}, | |
| "order": 6, | |
| "mode": 4, | |
| "inputs": [ | |
| { | |
| "name": "video", | |
| "type": "VIDEO", | |
| "link": 5 | |
| } | |
| ], | |
| "outputs": [], | |
| "properties": {}, | |
| "widgets_values": [ | |
| "video/Luma_Ray_3.2_T2V", | |
| "auto", | |
| "auto" | |
| ] | |
| }, | |
| { | |
| "id": 11, | |
| "type": "LoadImage", | |
| "pos": [ | |
| 170, | |
| 310 | |
| ], | |
| "size": [ | |
| 380, | |
| 370 | |
| ], | |
| "flags": {}, | |
| "order": 1, | |
| "mode": 0, | |
| "inputs": [], | |
| "outputs": [ | |
| { | |
| "name": "IMAGE", | |
| "type": "IMAGE", | |
| "links": [ | |
| 11 | |
| ] | |
| }, | |
| { | |
| "name": "MASK", | |
| "type": "MASK", | |
| "links": null | |
| } | |
| ], | |
| "properties": { | |
| "Node name for S&R": "LoadImage" | |
| }, | |
| "widgets_values": [ | |
| "cyber_cat.png", | |
| "image" | |
| ] | |
| }, | |
| { | |
| "id": 12, | |
| "type": "SaveVideo", | |
| "pos": [ | |
| 1120, | |
| 310 | |
| ], | |
| "size": [ | |
| 580, | |
| 770 | |
| ], | |
| "flags": {}, | |
| "order": 3, | |
| "mode": 0, | |
| "inputs": [ | |
| { | |
| "name": "video", | |
| "type": "VIDEO", | |
| "link": 10 | |
| } | |
| ], | |
| "outputs": [], | |
| "properties": {}, | |
| "widgets_values": [ | |
| "video/Luma_Ray_3.2_I2V", | |
| "auto", | |
| "auto" | |
| ] | |
| }, | |
| { | |
| "id": 13, | |
| "type": "LumaRay32ImageToVideoNode", | |
| "pos": [ | |
| 650, | |
| 310 | |
| ], | |
| "size": [ | |
| 400, | |
| 320 | |
| ], | |
| "flags": {}, | |
| "order": 2, | |
| "mode": 0, | |
| "inputs": [ | |
| { | |
| "name": "start_frame", | |
| "shape": 7, | |
| "type": "IMAGE", | |
| "link": 11 | |
| }, | |
| { | |
| "name": "end_frame", | |
| "shape": 7, | |
| "type": "IMAGE", | |
| "link": null | |
| } | |
| ], | |
| "outputs": [ | |
| { | |
| "name": "VIDEO", | |
| "type": "VIDEO", | |
| "links": [ | |
| 10 | |
| ] | |
| }, | |
| { | |
| "name": "generation_id", | |
| "type": "STRING", | |
| "links": [ | |
| 22, | |
| 23 | |
| ] | |
| } | |
| ], | |
| "properties": { | |
| "Node name for S&R": "LumaRay32ImageToVideoNode" | |
| }, | |
| "widgets_values": [ | |
| "Monochrome black and white mechanical robotic sphynx cat, seamless segmented metal skull, countless thick data cables flowing from neck like dreadlocks, glowing narrow vertical white slit eyes, sleek cybernetic feline body built like a cheetah for sprinting, full-body running sprint pose, low tracking parallel camera moves alongside the robot cat to capture dynamic fast running motion, camera slowly pull back wide to reveal the entire streamlined cyber cat body, futuristic cyberpunk city environment, towering neon-lit metallic skyscrapers, glowing circuit billboards, wet reflective asphalt ground with hologram reflections, dense tech wiring infrastructure, industrial sci-fi atmosphere, dramatic cinematic side lighting, high contrast monochrome, hyper detailed mechanical textures, scratch worn metal panels, intricate bolt and gear details, motion blur on paws and cable tails to emphasize speed, 8K ultra realistic, photorealistic, shallow dynamic motion blur, epic sci-fi cinematography, sharp industrial blueprint background subtle overlay texture, no text, no watermark", | |
| "720p", | |
| false, | |
| 569886435760230, | |
| "randomize" | |
| ], | |
| "color": "#432", | |
| "bgcolor": "#653" | |
| } | |
| ], | |
| "links": [ | |
| [ | |
| 5, | |
| 4, | |
| 0, | |
| 9, | |
| 0, | |
| "VIDEO" | |
| ], | |
| [ | |
| 10, | |
| 13, | |
| 0, | |
| 12, | |
| 0, | |
| "VIDEO" | |
| ], | |
| [ | |
| 11, | |
| 11, | |
| 0, | |
| 13, | |
| 0, | |
| "IMAGE" | |
| ], | |
| [ | |
| 22, | |
| 13, | |
| 1, | |
| 8, | |
| 0, | |
| "STRING" | |
| ], | |
| [ | |
| 23, | |
| 13, | |
| 1, | |
| 4, | |
| 0, | |
| "STRING" | |
| ] | |
| ], | |
| "groups": [ | |
| { | |
| "id": 1, | |
| "title": "Select and Ctrl-B to enable", | |
| "bounding": [ | |
| 2380, | |
| 300, | |
| 1000, | |
| 770 | |
| ], | |
| "color": "#3f789e", | |
| "flags": {} | |
| } | |
| ], | |
| "config": {}, | |
| "extra": { | |
| "ds": { | |
| "scale": 0.5424975779423886, | |
| "offset": [ | |
| 215.64003577404847, | |
| 128.38508536243685 | |
| ] | |
| }, | |
| "frontendVersion": "1.47.2" | |
| }, | |
| "version": 0.4 | |
| } | |
| { | |
| "id": "b277498e-2a80-4514-9bd6-3695ea8c1bbb", | |
| "revision": 0, | |
| "last_node_id": 23, | |
| "last_link_id": 23, | |
| "nodes": [ | |
| { | |
| "id": 4, | |
| "type": "LumaRay32ExtendVideoNode", | |
| "pos": [ | |
| 2430, | |
| 380 | |
| ], | |
| "size": [ | |
| 400, | |
| 324 | |
| ], | |
| "flags": {}, | |
| "order": 5, | |
| "mode": 4, | |
| "inputs": [ | |
| { | |
| "name": "source_generation_id", | |
| "type": "STRING", | |
| "widget": { | |
| "name": "source_generation_id" | |
| }, | |
| "link": 23 | |
| } | |
| ], | |
| "outputs": [ | |
| { | |
| "name": "VIDEO", | |
| "type": "VIDEO", | |
| "links": [ | |
| 5 | |
| ] | |
| }, | |
| { | |
| "name": "generation_id", | |
| "type": "STRING", | |
| "links": null | |
| } | |
| ], | |
| "properties": { | |
| "Node name for S&R": "LumaRay32ExtendVideoNode" | |
| }, | |
| "widgets_values": [ | |
| "", | |
| "Forward (continue after)", | |
| false, | |
| "", | |
| "720p", | |
| 86776790117141, | |
| "randomize" | |
| ], | |
| "color": "`#432`", | |
| "bgcolor": "`#653`" | |
| }, | |
| { | |
| "id": 7, | |
| "type": "MarkdownNote", | |
| "pos": [ | |
| 2440, | |
| 780 | |
| ], | |
| "size": [ | |
| 400, | |
| 240 | |
| ], | |
| "flags": {}, | |
| "order": 0, | |
| "mode": 0, | |
| "inputs": [], | |
| "outputs": [], | |
| "title": "Note: Extend Video", | |
| "properties": {}, | |
| "widgets_values": [ | |
| "This section is for extending videos; it requires a `generation_id` from the previous *Luma Ray 3.2* node.\n\n1. You can unlink the `source_generation_id` input and use the `id` shown on the `Preview as Text` node\n2. Enable it to extend video by default" | |
| ], | |
| "color": "`#222`", | |
| "bgcolor": "`#000`" | |
| }, | |
| { | |
| "id": 8, | |
| "type": "PreviewAny", | |
| "pos": [ | |
| 1780, | |
| 310 | |
| ], | |
| "size": [ | |
| 530, | |
| 230 | |
| ], | |
| "flags": {}, | |
| "order": 4, | |
| "mode": 0, | |
| "inputs": [ | |
| { | |
| "name": "source", | |
| "type": "*", | |
| "link": 22 | |
| } | |
| ], | |
| "outputs": [ | |
| { | |
| "name": "STRING", | |
| "type": "STRING", | |
| "links": null | |
| } | |
| ], | |
| "title": "Preview as Text (generation_id)", | |
| "properties": { | |
| "Node name for S&R": "PreviewAny" | |
| }, | |
| "widgets_values": [ | |
| null, | |
| null, | |
| null | |
| ] | |
| }, | |
| { | |
| "id": 9, | |
| "type": "SaveVideo", | |
| "pos": [ | |
| 2870, | |
| 380 | |
| ], | |
| "size": [ | |
| 450, | |
| 320 | |
| ], | |
| "flags": {}, | |
| "order": 6, | |
| "mode": 4, | |
| "inputs": [ | |
| { | |
| "name": "video", | |
| "type": "VIDEO", | |
| "link": 5 | |
| } | |
| ], | |
| "outputs": [], | |
| "properties": {}, | |
| "widgets_values": [ | |
| "video/Luma_Ray_3.2_T2V", | |
| "auto", | |
| "auto" | |
| ] | |
| }, | |
| { | |
| "id": 11, | |
| "type": "LoadImage", | |
| "pos": [ | |
| 170, | |
| 310 | |
| ], | |
| "size": [ | |
| 380, | |
| 370 | |
| ], | |
| "flags": {}, | |
| "order": 1, | |
| "mode": 0, | |
| "inputs": [], | |
| "outputs": [ | |
| { | |
| "name": "IMAGE", | |
| "type": "IMAGE", | |
| "links": [ | |
| 11 | |
| ] | |
| }, | |
| { | |
| "name": "MASK", | |
| "type": "MASK", | |
| "links": null | |
| } | |
| ], | |
| "properties": { | |
| "Node name for S&R": "LoadImage" | |
| }, | |
| "widgets_values": [ | |
| "cyber_cat.png", | |
| "image" | |
| ] | |
| }, | |
| { | |
| "id": 12, | |
| "type": "SaveVideo", | |
| "pos": [ | |
| 1120, | |
| 310 | |
| ], | |
| "size": [ | |
| 580, | |
| 770 | |
| ], | |
| "flags": {}, | |
| "order": 3, | |
| "mode": 0, | |
| "inputs": [ | |
| { | |
| "name": "video", | |
| "type": "VIDEO", | |
| "link": 10 | |
| } | |
| ], | |
| "outputs": [], | |
| "properties": {}, | |
| "widgets_values": [ | |
| "video/Luma_Ray_3.2_I2V", | |
| "auto", | |
| "auto" | |
| ] | |
| }, | |
| { | |
| "id": 13, | |
| "type": "LumaRay32ImageToVideoNode", | |
| "pos": [ | |
| 650, | |
| 310 | |
| ], | |
| "size": [ | |
| 400, | |
| 320 | |
| ], | |
| "flags": {}, | |
| "order": 2, | |
| "mode": 0, | |
| "inputs": [ | |
| { | |
| "name": "start_frame", | |
| "shape": 7, | |
| "type": "IMAGE", | |
| "link": 11 | |
| }, | |
| { | |
| "name": "end_frame", | |
| "shape": 7, | |
| "type": "IMAGE", | |
| "link": null | |
| } | |
| ], | |
| "outputs": [ | |
| { | |
| "name": "VIDEO", | |
| "type": "VIDEO", | |
| "links": [ | |
| 10 | |
| ] | |
| }, | |
| { | |
| "name": "generation_id", | |
| "type": "STRING", | |
| "links": [ | |
| 22, | |
| 23 | |
| ] | |
| } | |
| ], | |
| "properties": { | |
| "Node name for S&R": "LumaRay32ImageToVideoNode" | |
| }, | |
| "widgets_values": [ | |
| "Monochrome black and white mechanical robotic sphynx cat, seamless segmented metal skull, countless thick data cables flowing from neck like dreadlocks, glowing narrow vertical white slit eyes, sleek cybernetic feline body built like a cheetah for sprinting, full-body running sprint pose, low tracking parallel camera moves alongside the robot cat to capture dynamic fast running motion, camera slowly pull back wide to reveal the entire streamlined cyber cat body, futuristic cyberpunk city environment, towering neon-lit metallic skyscrapers, glowing circuit billboards, wet reflective asphalt ground with hologram reflections, dense tech wiring infrastructure, industrial sci-fi atmosphere, dramatic cinematic side lighting, high contrast monochrome, hyper detailed mechanical textures, scratch worn metal panels, intricate bolt and gear details, motion blur on paws and cable tails to emphasize speed, 8K ultra realistic, photorealistic, shallow dynamic motion blur, epic sci-fi cinematography, sharp industrial blueprint background subtle overlay texture, no text, no watermark", | |
| "720p", | |
| false, | |
| 569886435760230, | |
| "randomize" | |
| ], | |
| "color": "`#432`", | |
| "bgcolor": "`#653`" | |
| } | |
| ], | |
| "links": [ | |
| [ | |
| 5, | |
| 4, | |
| 0, | |
| 9, | |
| 0, | |
| "VIDEO" | |
| ], | |
| [ | |
| 10, | |
| 13, | |
| 0, | |
| 12, | |
| 0, | |
| "VIDEO" | |
| ], | |
| [ | |
| 11, | |
| 11, | |
| 0, | |
| 13, | |
| 0, | |
| "IMAGE" | |
| ], | |
| [ | |
| 22, | |
| 13, | |
| 1, | |
| 8, | |
| 0, | |
| "STRING" | |
| ], | |
| [ | |
| 23, | |
| 13, | |
| 1, | |
| 4, | |
| 0, | |
| "STRING" | |
| ] | |
| ], | |
| "groups": [ | |
| { | |
| "id": 1, | |
| "title": "Select and Ctrl-B to enable", | |
| "bounding": [ | |
| 2380, | |
| 300, | |
| 1000, | |
| 770 | |
| ], | |
| "color": "`#3f789e`", | |
| "flags": {} | |
| } | |
| ], | |
| "config": {}, | |
| "extra": { | |
| "ds": { | |
| "scale": 0.5424975779423886, | |
| "offset": [ | |
| 215.64003577404847, | |
| 128.38508536243685 | |
| ] | |
| }, | |
| "frontendVersion": "1.47.2" | |
| }, | |
| "properties": { | |
| "models": [ | |
| { | |
| "name": "luma_ray3_3_i2v", | |
| "thumbnail": "api_luma_ray3_3_i2v-1.webp", | |
| "url": "https://<model-download-url>", | |
| "sha256": "<sha256>" | |
| } | |
| ] | |
| }, | |
| "version": 0.4 | |
| } |
🧰 Tools
🪛 OpenGrep (1.22.0)
[ERROR] 335-335: Possible credit card number (PAN) detected in source code. Credit card numbers should never be hardcoded or stored in source files. Use a secrets manager or tokenization service instead.
(coderabbit.pii.credit-card-number)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@templates/api_luma_ray3_3_i2v.json` around lines 1 - 344, The template file
is missing required embedded model metadata in the root-level properties object.
Add a models array to the properties field containing entries with download URLs
and SHA256 hashes for each model used by the LumaRay32ImageToVideoNode and
LumaRay32ExtendVideoNode nodes. Additionally, create and add a thumbnail image
file named api_luma_ray3_3_i2v-1.webp in the templates directory that visually
represents this workflow template to comply with the repository's template
contract requirements.
Source: Coding guidelines
| "outputs": [], | ||
| "properties": {}, | ||
| "widgets_values": [ | ||
| "video/Luma_Ray_3.2_T2V", |
There was a problem hiding this comment.
I2V template is saving with a T2V prefix.
"video/Luma_Ray_3.2_T2V" is inconsistent with this I2V workflow and can mix output organization across template types.
Quick fix
- "video/Luma_Ray_3.2_T2V",
+ "video/Luma_Ray_3.2_I2V",📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| "video/Luma_Ray_3.2_T2V", | |
| "video/Luma_Ray_3.2_I2V", |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@templates/api_luma_ray3_3_i2v.json` at line 146, The video path prefix in the
I2V template incorrectly uses "T2V" (Text-to-Video) instead of "I2V"
(Image-to-Video), which causes inconsistent output organization between template
types. Change the string "video/Luma_Ray_3.2_T2V" to use the "I2V" suffix
instead of "T2V" to properly reflect the template's purpose and maintain
consistent output directory structure.
| { | ||
| "name": "api_luma_ray3_3_i2v", | ||
| "title": "Luma Ray 3.2: Image to Video", | ||
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", |
There was a problem hiding this comment.
Correct the i2v description so it doesn’t describe t2v behavior.
Line 8815 says this template generates video “from text prompts,” but this entry is api_luma_ray3_3_i2v (image-to-video). Right model, wrong yodel—this will mislead users in the catalog.
💡 Suggested patch
- "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.",
+ "description": "Generate cinematic-quality videos from an input image using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.",📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", | |
| "description": "Generate cinematic-quality videos from an input image using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@templates/index.ar.json` at line 8815, The description for the
api_luma_ray3_3_i2v template entry is incorrectly describing text-to-video
behavior by mentioning "from text prompts," when this is an image-to-video
template. Update the description field to accurately reflect image-to-video
functionality by removing the reference to text prompts and instead focusing on
how the template generates videos from input images, making it clear this is an
image-to-video tool rather than text-to-video.
| { | ||
| "name": "api_luma_ray3_3_i2v", | ||
| "title": "Luma Ray 3.2: Image to Video", | ||
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", |
There was a problem hiding this comment.
Description mismatches the i2v template intent.
Line 8815 says this template generates video “from text prompts,” but this entry is api_luma_ray3_3_i2v and tagged image-to-video. That mismatch can send users down the wrong node-road.
Suggested fix
- "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.",
+ "description": "Generate cinematic-quality videos from input images using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.",📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", | |
| "description": "Generate cinematic-quality videos from input images using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@templates/index.ko.json` at line 8815, The description for the
api_luma_ray3_3_i2v template entry incorrectly describes the template as
generating videos "from text prompts," which contradicts the image-to-video
(i2v) nature of the template. Update the description field to accurately reflect
that this is an image-to-video conversion template, emphasizing that it accepts
images as primary input and converts them to videos, rather than generating from
text prompts. Ensure the description clearly conveys the image-to-video workflow
to guide users to the correct template for their use case.
Comment on lines
+8814
to
+8815
| "title": "Luma Ray 3.2: Image to Video", | ||
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", |
There was a problem hiding this comment.
Fix locale and modality mismatch in the new api_luma_ray3_3_i2v catalog entry.
Line 8814–8815 are English in index.ru.json, and Line 8815 says “from text prompts” for an i2v template. That’s a metadata rhyme gone wrong: image-to-video by name, text-to-video by claim.
Suggested patch
- "title": "Luma Ray 3.2: Image to Video",
- "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.",
+ "title": "Luma Ray 3.2: Изображение в Видео",
+ "description": "Создавайте кинематографичные видео из входного изображения с помощью Luma Ray 3.2, с поддержкой продления предыдущих генераций по generation ID. Рабочий процесс принимает 1 входное изображение и выдаёт 1 видео, что удобно для итеративной доработки. Подходит для коротких киносцен, маркетингового контента и профессионального видеопроизводства.",As per coding guidelines, "Support 11 languages in templates: en (default), zh, zh-TW, ja, ko, es, fr, ru, tr, ar, pt-BR; maintain corresponding index.{locale}.json files for each locale".
📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| "title": "Luma Ray 3.2: Image to Video", | |
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", | |
| "title": "Luma Ray 3.2: Изображение в Видео", | |
| "description": "Создавайте кинематографичные видео из входного изображения с помощью Luma Ray 3.2, с поддержкой продления предыдущих генераций по generation ID. Рабочий процесс принимает 1 входное изображение и выдаёт 1 видео, что удобно для итеративной доработки. Подходит для коротких киносцен, маркетингового контента и профессионального видеопроизводства.", |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@templates/index.ru.json` around lines 8814 - 8815, The title and description
fields for the api_luma_ray3_3_i2v catalog entry in index.ru.json are written in
English instead of Russian, violating the locale requirement for the .ru.json
file. Additionally, the description incorrectly states "from text prompts" for
an image-to-video template when it should reference generating from images.
Translate both the title "Luma Ray 3.2: Image to Video" and the description to
Russian, and correct the description to accurately reflect that videos are
generated from input images rather than text prompts, ensuring the modality
description matches the i2v template type.
Source: Coding guidelines
Comment on lines
+8813
to
+8816
| "name": "api_luma_ray3_3_i2v", | ||
| "title": "Luma Ray 3.2: Image to Video", | ||
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", | ||
| "mediaType": "image", |
There was a problem hiding this comment.
api_luma_ray3_3_i2v description mismatches the template modality.
Line 8815 says this i2v template generates video “from text prompts,” which conflicts with both the template name and the same description’s “1 input image” statement—bit of a rhyme crime for users.
Suggested fix
- "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.",
+ "description": "Generate cinematic-quality videos from an input image using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.",🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@templates/index.tr.json` around lines 8813 - 8816, The description for the
api_luma_ray3_3_i2v template object incorrectly states it generates videos "from
text prompts" when this is an image-to-video template that accepts image inputs,
not text inputs. Update the description field to remove the reference to text
prompts and accurately describe that the template generates videos from a single
input image, ensuring consistency with the template name (i2v stands for
image-to-video) and the earlier statement about accepting "1 input image".
| { | ||
| "name": "api_luma_ray3_3_i2v", | ||
| "title": "Luma Ray 3.2: Image to Video", | ||
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", |
There was a problem hiding this comment.
Fix i2v description mismatch (text prompt vs image input).
Line 8815 says this template generates video “from text prompts,” but this entry is api_luma_ray3_3_i2v and later says it accepts 1 input image. That contradiction can confuse users browsing templates.
Suggested patch (quick rhyme, zero grime)
- "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.",
+ "description": "Generate cinematic-quality videos from an input image using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.",📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", | |
| "description": "Generate cinematic-quality videos from an input image using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@templates/index.zh-TW.json` at line 8815, The description for the
api_luma_ray3_3_i2v template entry incorrectly states it generates videos "from
text prompts" when this is an image-to-video template that accepts 1 input
image. Update the description to correctly reflect that it generates
cinematic-quality videos from image inputs rather than text prompts, while
keeping the rest of the description about supporting generation extension and
iterative refinement relevant to the image-to-video use case.
| { | ||
| "name": "api_luma_ray3_3_i2v", | ||
| "title": "Luma Ray 3.2: Image to Video", | ||
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", |
There was a problem hiding this comment.
Description conflicts with the i2v template type.
Line 8815 says video is generated “from text prompts,” but this entry is api_luma_ray3_3_i2v with 图生视频 tags. That wording reads like t2v—same beat, wrong street.
💡 Suggested fix
- "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.",
+ "description": "使用 Luma Ray 3.2 从输入图像生成电影级视频，并支持通过已有 generation ID 扩展先前生成结果。该工作流接收 1 张输入图像并输出 1 个视频，便于无缝迭代优化。适用于短片创作、营销内容和专业视频制作。"📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", | |
| "description": "使用 Luma Ray 3.2 从输入图像生成电影级视频，并支持通过已有 generation ID 扩展先前生成结果。该工作流接收 1 张输入图像并输出 1 个视频，便于无缝迭代优化。适用于短片创作、营销内容和专业视频制作。" |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@templates/index.zh.json` at line 8815, The description for the
api_luma_ray3_3_i2v template incorrectly states that videos are generated "from
text prompts" when this is an image-to-video template, not text-to-video. Update
the description text at line 8815 to remove the reference to "text prompts" and
replace it with wording that accurately reflects the image-to-video
functionality, making clear that the input is an image (not text) that gets
transformed into video output.
Align the template id with its text-to-video workflow by renaming api_luma_ray3_3_t2i to api_luma_ray3_3_t2v across assets, bundles, and index metadata.
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
templates/index.fa.json (1)
8814-8815:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winLocalize the new
api_luma_ray3_3_i2vcopy inindex.fa.json.Line 8814 and Line 8815 are still English in the Persian catalog. Quick l10n fix, big UX win—make it Farsi so the locale doesn’t feel far‑see.
Suggested patch
- "title": "Luma Ray 3.2: Image to Video", - "description": "Generate cinematic-quality videos from text prompts using Luma Ray 3.2, with support for extending previous generations by providing a generation ID. The workflow accepts 1 input image and produces 1 video output, enabling seamless iterative refinement. Ideal for creating short film sequences, marketing content, and professional video production.", + "title": "Luma Ray 3.2: تصویر به ویدیو", + "description": "با Luma Ray 3.2 ویدیوهای سینمایی باکیفیت از تصویر تولید کنید و با ارائه generation ID خروجیهای قبلی را گسترش دهید. این گردش کار یک تصویر ورودی دریافت کرده و یک ویدیو خروجی تولید میکند و برای تکرار سریع، ساخت سکانسهای کوتاه، محتوای بازاریابی و تولید حرفهای ویدیو مناسب است.",🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@templates/index.fa.json` around lines 8814 - 8815, In the index.fa.json file, locate the `api_luma_ray3_3_i2v` entry and translate the English title "Luma Ray 3.2: Image to Video" and its description about generating cinematic-quality videos from text prompts into Persian. Ensure both the title and description fields are fully translated to maintain consistent localization across the Persian language catalog.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Outside diff comments:
In `@templates/index.fa.json`:
- Around line 8814-8815: In the index.fa.json file, locate the
`api_luma_ray3_3_i2v` entry and translate the English title "Luma Ray 3.2: Image
to Video" and its description about generating cinematic-quality videos from
text prompts into Persian. Ensure both the title and description fields are
fully translated to maintain consistent localization across the Persian language
catalog.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 5780b894-853e-4c60-8524-112c8e769fd3
📒 Files selected for processing (16)
bundles.jsonscripts/i18n.jsontemplates/api_luma_ray3_3_t2v-1.webptemplates/api_luma_ray3_3_t2v.jsontemplates/index.ar.jsontemplates/index.es.jsontemplates/index.fa.jsontemplates/index.fr.jsontemplates/index.ja.jsontemplates/index.jsontemplates/index.ko.jsontemplates/index.pt-BR.jsontemplates/index.ru.jsontemplates/index.tr.jsontemplates/index.zh-TW.jsontemplates/index.zh.json
💤 Files with no reviewable changes (1)
- templates/api_luma_ray3_3_t2v.json
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Changes Summary
✨ New Templates (1)
api_luma_ray3_3_t2iDetails
This PR contains updates to the ComfyUI workflow templates.
📝 Created via ComfyUI Template Manager
Branch:
template-update-20260618-162056Repository:
comfyui-wiki/workflow_templates📊 View changes in Template Manager: http://localhost:3000/?pr=951