New: add a new plugin tongyi_aigc-0.0.1.difypkg【TongYi AIGC: Supports full-featured image and video generation using the latest Alibaba Tongyi models (wan2.6, qwen-image, Z-image, wan2.5, wan2.2, and wanx2.1).】#2088
Merged
crazywoola merged 2 commits intolanggenius:mainfrom Feb 24, 2026
Conversation
… full-featured image and video generation using the latest Alibaba Tongyi models (wan2.6, qwen-image, Z-image, wan2.5, wan2.2, and wanx2.1).】
crazywoola
requested changes
Feb 24, 2026
Member
crazywoola
left a comment
crazywoola
left a comment
There was a problem hiding this comment.
PR Review Results
| Check | Status | Required Action |
|---|---|---|
| Single .difypkg | ✅ Pass | - |
| PR language (no CJK) | ✅ Pass | - |
| Project structure | ✅ Pass | - |
| Manifest author | ✅ Pass | - |
| Icon valid | ❌ Fail | Error checking icon: 'utf-8' codec can't decode byte 0x89 in position 0: invalid start byte |
| Version not exists | ✅ Pass | - |
| README language (no Chinese) | ✅ Pass | - |
| PRIVACY.md exists | ✅ Pass | - |
| Dependencies install | ✅ Pass | - |
| dify_plugin >= 0.5.0 | ❌ Fail | dify_plugin version 0.2.0 is too old (need >= 0.5.0) |
| Install test | ❌ Fail | Install test failed: Testing plugin in directory: /var/folders/c5/ssq8b54n0rj6rbmghy7_2xdm0000gn/T/tmpmg9s9_cr/repo/unpacked_plugin |
| {"version":"0.0.1","type":"plugin","author":"sawyer-shi","name":"tongyi_aigc","repo":"https://github.com/sawyer-shi/dify-plugins-tongyi_aigc","description":{"zh_Hans":"通义AIGC：支持全套图片+视频的生成、编辑等操作，使用最新的阿里通义模型(wan2.6、qwen-image、Z-Image以及wan2.5、wan2.2和wanx2.1)。","pt_BR":"TongYi AIGC: Supports full-featured image and video generation using the latest Alibaba Tongyi models (wan2.6, qwen-image, Z-image, wan2.5, wan2.2, and wanx2.1).","ja_JP":"TongYi AIGC: Supports full-featured image and video generation using the latest Alibaba Tongyi models (wan2.6, qwen-image, Z-image, wan2.5, wan2.2, and wanx2.1).","en_US":"TongYi AIGC: Supports full-featured image and video generation using the latest Alibaba Tongyi models (wan2.6, qwen-image, Z-image, wan2.5, wan2.2, and wanx2.1)."},"icon":"icon.png","icon_dark":null,"label":{"zh_Hans":"通义AIGC","pt_BR":"TongYi AIGC","ja_JP":"TongYi AIGC","en_US":"TongYi AIGC"},"created_at":"2026-02-15T11:19:55.825854+08:00","resource":{"memory":268435456,"permission":{"tool":{"enabled":true},"model":{"enabled":true,"llm":false,"text_embedding":false,"rerank":false,"tts":false,"speech2text":false,"moderation":false},"node":null,"endpoint":{"enabled":true},"app":{"enabled":true},"storage":{"enabled":true,"size":1048576}}},"plugins":{"tools":["provider/tongyi_aigc.yaml"],"models":[],"endpoints":[],"agent_strategies":[],"datasources":[],"triggers":[]},"meta":{"version":"0.0.1","arch":["amd64","arm64"],"runner":{"language":"python","version":"3.12","entrypoint":"main"},"minimum_dify_version":null}} |
{"event": "log", "data": {"level": "INFO", "message": "Installed tool: tongyi_aigc", "timestamp": 1771898285.011931}}
{"event":"heartbeat","session_id":null,"data":{}}
{"event":"heartbeat","session_id":null,"data":{}}
!!! Force exit after 20 seconds
!!! Plugin test result: failed
!!! Process exited, here is the stderr:
================================================
!!! Have you tested it locally?
|
| Packaging test | ✅ Pass | - |
Next steps
Please address the failed checks above.
crazywoola
requested changes
Feb 24, 2026
Member
crazywoola
left a comment
crazywoola
left a comment
There was a problem hiding this comment.
Re-review (concise)
Re-reviewed with concise notes (raw logs removed from the review body).
| Check | Status | Required action |
|---|---|---|
dify_plugin >= 0.5.0 |
❌ Fail | Update the plugin dependency to dify_plugin>=0.5.0. |
| Install verification | ❌ Fail | Install validation did not pass in reviewer pre-check. Please use CI logs to identify and fix the root cause. |
| Packaging test | ✅ Pass | No action needed. |
Next steps
- Bump
dify_pluginto>=0.5.0. - Re-run CI and confirm install verification passes.
- Push updates and request re-review.
… full-featured image and video generation using the latest Alibaba Tongyi models (wan2.6, qwen-image, Z-image, wan2.5, wan2.2, and wanx2.1).】
crazywoola
approved these changes
Feb 24, 2026
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
2 participants
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.
TongYi AIGC
A powerful Dify plugin providing comprehensive AI-powered image and video generation capabilities using Alibaba Cloud Tongyi's latest Wanxiang, Qwen, and Z-Image models. Supports text-to-image, text-to-video, image-to-image, image-to-video, image translation, and more with professional-grade quality and flexible configuration options.
Version Information
Version History
Quick Start
Key Features
Core Features
Image Generation
Wan Text to Image (wan_text_2_image)
Generate images from text descriptions using Wanxiang models.
Wan Image to Image (wan_image_2_image)
Generate images from text and reference images using Wanxiang models.
Qwen Text to Image (qwen_text_2_image)
Generate images using Qwen image models.
Qwen Image to Image (qwen_image_2_image)
Generate images from text and reference images using Qwen models.
Z-Image Text to Image (z_image_text_2_image)
Generate images using Z-Image Turbo model.
Image Translation (qwen_image_translate)
Translate text in images with AI-powered OCR and translation.
Video Generation
Text to Video (wan_text_2_video)
Generate videos from text descriptions using Wanxiang models.
Image to Video (wan_first_image_2_video)
Generate video from a single image with text description.
First-Last Frame Video (wan_first_end_image_2_video)
Generate video from first and last frame images.
Reference Video (wan_reference_video)
Generate videos based on reference video style.
Video Query (wan_video_query)
Query the status and results of video generation tasks.
Image Translation Query (qwen_image_translate_query)
Query image translation task status and results.
Technical Advantages
Requirements
Installation & Configuration
Install the required dependencies:
Configure your Alibaba Cloud API credentials in the plugin settings:
Install the plugin in your Dify environment
Usage
Image Generation Tools
1. Wan Text to Image
Generate images from text descriptions.
model: Model version (default: wan2.6-t2i)prompt: Text description of the image (required, <=2100 chars)negative_prompt: Describe what you don't want (<=500 chars)size: Image size (default: 1280*1280)n: Number of images to generate (1-4, default: 3)prompt_extend: Enable prompt intelligent rewriting (default: true)watermark: Enable/disable watermark (default: true)seed: Random seed for reproducibility2. Wan Image to Image
Generate images from text and reference images.
model: Model version (default: wan2.6-image)prompt: Text description (required, <=2000 chars)images: Reference image files (1-4 images, required)size: Image size (default: 1280*1280)n: Number of images to generate (1-4, default: 3)enable_interleave: Enable interleaved output (default: false)prompt_extend: Enable prompt intelligent rewriting (default: true)watermark: Enable/disable watermark (default: true)3. Qwen Text to Image
Generate images using Qwen models.
prompt: Text description (required)model: Model version (default: qwen-image-max)size: Image size (default: 1664*928)negative_prompt: Describe what you don't wantprompt_extend: Enable prompt intelligent rewritingwatermark: Enable/disable watermark (default: true)seed: Random seed for reproducibility4. Qwen Image to Image
Generate images from text and reference images using Qwen models.
prompt: Text description (required)images: Reference image files (1-3 images, required)model: Model version (default: qwen-image-edit-max)size: Image size (default: 1024*1024)n: Number of images to generate (1-6, default: 3)prompt_extend: Enable prompt intelligent rewritingwatermark: Enable/disable watermark (default: true)5. Z-Image Text to Image
Generate images using Z-Image Turbo.
prompt: Text description (required, <=800 chars)model: Model version (default: z-image-turbo)size: Image size (default: 1024*1536)prompt_extend: Enable prompt intelligent rewriting (default: false)seed: Random seed for reproducibility6. Image Translation
Translate text in images.
image_url: Image URL for translation (required)target_lang: Target language (required)source_lang: Source language (default: auto)domain_hint: Domain hint for improved translationsensitives: Sensitive words (JSON array)terminologies: Terminologies (JSON array)model: Model version (default: qwen-mt-image)Video Generation Tools
7. Text to Video
Generate videos from text descriptions.
model: Model version (default: wan2.6-t2v)prompt: Text description (required)negative_prompt: Describe what you don't wantsize: Video resolution (default: 1920*1080)duration: Duration in seconds (model dependent, default: 5)audio_url: Custom audio file URLaudio: Auto generate audio (default: true)shot_type: Single or multi shot (default: single)prompt_extend: Enable prompt intelligent rewriting (default: true)watermark: Enable/disable watermark (default: true)seed: Random seed for reproducibility8. Image to Video
Generate video from a single image.
model: Model version (default: wan2.6-i2v)prompt: Text descriptionimage_input: Input image fileresolution: Video resolution (default: 1080P)duration: Duration in seconds (model dependent, default: 5)template: Video effect templateaudio_url: Custom audio file URLaudio: Auto generate audio (default: true)shot_type: Single or multi shot (default: single)prompt_extend: Enable prompt intelligent rewriting (default: true)watermark: Enable/disable watermark (default: true)9. First-Last Frame Video
Generate video from first and last frame images.
model: Model version (default: wan2.2-kf2v-flash)prompt: Text descriptionfirst_frame_image: First frame image (required)last_frame_image: Last frame imageresolution: Video resolution (default: 720P)template: Video effect templateprompt_extend: Enable prompt intelligent rewriting (default: true)watermark: Enable/disable watermark (default: true)10. Reference Video
Generate videos based on reference video style.
model: Model version (default: wan2.6-r2v)prompt: Text description (required, max 1500 chars)reference_urls: Reference URLs (videos or images, max 5)size: Video resolution (default: 1920*1080)duration: Duration in seconds (2-10, default: 5)shot_type: Single or multi shot (default: single)audio: Auto generate audio (default: true, wan2.6-r2v-flash only)watermark: Enable/disable watermark (default: true)11. Video Query
Query video generation task status.
task_id: Video generation task ID (required)download_video: Download video when available (default: false)12. Image Translation Query
Query image translation task status.
task_id: Translation task ID (required)Notes
Developer Information
https://github.com/sawyer-shihttps://github.com/sawyer-shi/dify-plugins-tongyi_aigcLicense Notice
This project is licensed under Apache License 2.0. See LICENSE file for full license text.
Ready to create stunning images and videos with AI?
Plugin Submission Form
1. Metadata
2. Submission Type
3. Description
4. Checklist
5. Documentation Checklist
Please confirm that your plugin README includes all necessary information:
6. Privacy Protection Information
Based on Dify Plugin Privacy Protection Guidelines:
Data Collection
Privacy Policy