Skip to content

feat: Add CometAPI model provider plugin#2

Merged
NoahCodeGG merged 2 commits intomainfrom
develop
Aug 7, 2025
Merged

feat: Add CometAPI model provider plugin#2
NoahCodeGG merged 2 commits intomainfrom
develop

Conversation

@tensornull
Copy link
Collaborator

@tensornull tensornull commented Aug 7, 2025 •
edited
Loading

Related Issues or Context

  • Add CometAPI model provider plugin

    feat: Complete CometAPI model provider plugin with 500+ AI models support

    • Add CometAPI model provider with comprehensive API integration
    • Support for LLM, text embedding, TTS, and speech-to-text models
    • Include multilingual descriptions (EN/JP/ZH/PT-BR)
    • Implement common OpenAI-compatible interface for model integration

This PR contains Changes to Non-Plugin

  • Documentation
  • Other

This PR contains Changes to Non-LLM Models Plugin

  • I have Run Comprehensive Tests Relevant to My Changes

    1. Installation
    image
    1. Setup CometAPI Key
    image
    1. Get the supported models
    image

    1. Try to test for CometAPI

      !image

This PR contains Changes to LLM Models Plugin

  • Other Changes (Add New Models, Fix Model Parameters etc.)
    Provide CometAPI support for Dify.
image

Version Control (Any Changes to the Plugin Will Require Bumping the Version)

  • I have Bumped Up the Version in Manifest.yaml (Top-Level Version Field, Not in Meta Section)

Dify Plugin SDK Version

Environment Verification (If Any Code Changes)

SaaS Environment

  • I have Tested My Changes on cloud.dify.ai with a Clean Environment That Matches the Production Configuration
    • Python Virtual Env Matching Manifest.yaml & requirements.txt

tensornull and others added 2 commits August 7, 2025 11:16
@tensornull
feat: Complete CometAPI model provider plugin with 500+ AI models sup…
3934c15 
…port

- Add CometAPI model provider with comprehensive API integration
- Support for LLM, text embedding, TTS, and speech-to-text models
- Include multilingual descriptions (EN/JP/ZH/PT-BR)
- Add proper plugin structure with manifest, provider configs, and assets
- Implement common OpenAI-compatible interface for model integration
@tensornull
feature: Better multi-language support
4ef7872
@tensornull tensornull marked this pull request as ready for review August 7, 2025 05:43
@NoahCodeGG NoahCodeGG merged commit 668dc60 into main Aug 7, 2025
tensornull pushed a commit that referenced this pull request Sep 11, 2025
@yt-koike
feat: ComfyUI 0.2.3 (langgenius#1537)
84a9edc 
* add list_models node

* add img2img node

* rename stable_diffusion node to txt2img

* add img2img.json

* register txt2img, img2img and list_models node

* bugfix

* add depth_anything and depth_pro

* Merge pull request #2 from yt-koike/2vid

add img2img and img2vid

* verify samplers and schedulers

* refactor

* refactor

* prompt installing depth related plugins on ComfyUI

* version up dify_plugin

* add ja_JP

* tune img2vid

* add face_swap feature

* add install prompt

* bugfix & add ja_JP translations

* refactor

* add translation

* bump: comfyui to 0.0.9

* format fix

* add upscale feature

* Merge list_upscalers to list_models

* add downloaders

* refactor

* add list LORAs

* change output name

* variable length LORAs

* add localisation

* add localisation and errors

* update README.md

* fix urls in README.md

* small edit on README.md

* shrink AIR.png

* raise Errors instead of text messages

* bugfix when empty LORAs

* optionalize CivitAI model version

* rename files

* fix:workflow

* Update comfyui.yaml

* bugfix

* token support for Huggingface

* Update README.md

* Update README.md

* Update download_civitai.yaml

* Change error messages

* small fix

* bugfix

* change error message

* add json/

* bump up to 0.1.2

* rename post_image() to upload_image()

* add generate() and rename variables

* URL bugfix

* support arbitrary output from multiple nodes

* 202560531

* change requirements.txt

* introduce comfy.generate()

* mime related refactor

* bugfix

* add localisations

* support HiresFix

* download public version

* downloader update

* update requirements.txt

* update README.md

* UI change on HiresFix

* more detailed error messages

* 20250701

* fetch AIR of CivitAI models

* integrate upscale to Image Edit

* accept None for node_id

* add better error message

* simplify list_model's output

* accept custom model for img2vid

* bugfix

* rename one image_edit feature

* update README.md

* 20250702

* clean up unused imports

* make samplers and schedulers required

* fix documents

* bump requirements.txt

* ComfyUI v0.2.0 update

* ComfyUI 0.2.0 update

* update general data

* refactor workflow

* add example DSLs

* size bugfix

* LORA bugfix

* bump to 0.2.1

* introduce model_manager

* bugfix

* add batch_size parameter

* introduce model_manager to more methods

* update document

* refactor

* rm unused imports

* bugfix

* support api_key_comfy_org

* replace get_civit_key() and get_hf_key()

* add download_from_json()

* add wan2.2 t2v

* add convert_to_api_ready()

* add convert_to_api.py

* edit run_workflow.yaml

* unify clean_json_string()

* add reference.txt

* add enable_download switch

* fix json load bug

* separate widgets_value to a file

* json format fix

* update wan 2.2 14B json

* add Wan 2.2 14B

* more detailed ComfyUI error

* enable download by default

* support FLUX workflow

* ignore disable nodes

* Change Docker image tag

* add LoraLoader to widgets_value_names.json

* update wan2_2 json
tensornull pushed a commit that referenced this pull request Sep 11, 2025
@yt-koike
feat: ComfyUI 0.2.4 (langgenius#1604)
f5a8c9e 
* add list_models node

* add img2img node

* rename stable_diffusion node to txt2img

* add img2img.json

* register txt2img, img2img and list_models node

* bugfix

* add depth_anything and depth_pro

* Merge pull request #2 from yt-koike/2vid

add img2img and img2vid

* verify samplers and schedulers

* refactor

* refactor

* prompt installing depth related plugins on ComfyUI

* version up dify_plugin

* add ja_JP

* tune img2vid

* add face_swap feature

* add install prompt

* bugfix & add ja_JP translations

* refactor

* add translation

* bump: comfyui to 0.0.9

* format fix

* add upscale feature

* Merge list_upscalers to list_models

* add downloaders

* refactor

* add list LORAs

* change output name

* variable length LORAs

* add localisation

* add localisation and errors

* update README.md

* fix urls in README.md

* small edit on README.md

* shrink AIR.png

* raise Errors instead of text messages

* bugfix when empty LORAs

* optionalize CivitAI model version

* rename files

* fix:workflow

* Update comfyui.yaml

* bugfix

* token support for Huggingface

* Update README.md

* Update README.md

* Update download_civitai.yaml

* Change error messages

* small fix

* bugfix

* change error message

* add json/

* bump up to 0.1.2

* rename post_image() to upload_image()

* add generate() and rename variables

* URL bugfix

* support arbitrary output from multiple nodes

* 202560531

* change requirements.txt

* introduce comfy.generate()

* mime related refactor

* bugfix

* add localisations

* support HiresFix

* download public version

* downloader update

* update requirements.txt

* update README.md

* UI change on HiresFix

* more detailed error messages

* 20250701

* fetch AIR of CivitAI models

* integrate upscale to Image Edit

* accept None for node_id

* add better error message

* simplify list_model's output

* accept custom model for img2vid

* bugfix

* rename one image_edit feature

* update README.md

* 20250702

* clean up unused imports

* make samplers and schedulers required

* fix documents

* bump requirements.txt

* ComfyUI v0.2.0 update

* ComfyUI 0.2.0 update

* update general data

* refactor workflow

* add example DSLs

* size bugfix

* LORA bugfix

* bump to 0.2.1

* introduce model_manager

* bugfix

* add batch_size parameter

* introduce model_manager to more methods

* update document

* refactor

* rm unused imports

* bugfix

* support api_key_comfy_org

* replace get_civit_key() and get_hf_key()

* add download_from_json()

* add wan2.2 t2v

* add convert_to_api_ready()

* add convert_to_api.py

* edit run_workflow.yaml

* unify clean_json_string()

* add reference.txt

* add enable_download switch

* fix json load bug

* separate widgets_value to a file

* json format fix

* update wan 2.2 14B json

* add Wan 2.2 14B

* more detailed ComfyUI error

* enable download by default

* support FLUX workflow

* ignore disable nodes

* Change Docker image tag

* add LoraLoader to widgets_value_names.json

* update wan2_2 json

* 20250824

* refactor ComfyUI Workflow

* introduce quickstart.py

* 20250825

* renew qwen related json

* add set_SD3_latent_image()

* add quickstart node

* rename image_edit node to img2any

* add flux_dev_fp8

* add QuickStart to nodes.png

* randomize flux seed

* introduce ComfyUiFile

* output workflow as text

* introduce ComfyUiFile

* explain QuickStart on README.md

* change KSampler params

* intoruce decode_lora()

* explain how to set LORA strength

* rm duplicates

* change civitai model ID and introduce get_civitai_workflow()

* Update README.md
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@NoahCodeGG NoahCodeGG NoahCodeGG approved these changes

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@tensornull @NoahCodeGG