[PR #17734] [CLOSED] [Microservice] Add ComfyUI Service with Fal.ai IntegrationFeat/perry comfyui deployment #11326

New Issue

2025-11-11T19:28:53-06:00

GiteaMirror commented

2025-11-11 19:28:53 -06:00

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/17734
Author: @PerryPAN219
Created: 9/25/2025
Status: ❌ Closed

Base: main ← Head: feat/perry-comfyui-deployment

📝 Commits (2)

3e95e7c Scaffold Setup, setup guide and updated docker-compose configuration:
48cde43 Add ComfyUI service with image-to-image Fal.ai integration

📊 Changes

12 files changed (+1364 additions, -13 deletions)

View changed files

📝 backend/open_webui/config.py (+13 -0)
📝 backend/open_webui/env.py (+1 -0)
➕ comfyui-service/.gitignore (+62 -0)
➕ comfyui-service/Dockerfile (+35 -0)
➕ comfyui-service/README.md (+126 -0)
➕ comfyui-service/api/__init__.py (+7 -0)
➕ comfyui-service/api/routes.py (+571 -0)
➕ comfyui-service/docker-compose.yml (+31 -0)
➕ comfyui-service/main.py (+230 -0)
➕ comfyui-service/requirements.txt (+9 -0)
📝 docker-compose.yaml (+24 -13)
➕ setupguide.md (+255 -0)

📄 Description

Summary

This PR introduces a new ComfyUI Microservice for AI image generation, integrated into the CerebraUI platform.
It provides core workflows (text-to-image, image-to-image, multimodal, and fashion transfer) with FastAPI-based endpoints.

Key Features

Independent microservice at port 8001
Text-to-image, image-to-image, multimodal, and fashion transfer endpoints
File upload validation (JPEG, PNG, WebP, BMP, TIFF, GIF; max 10MB)
Rate limiting (15 requests/minute per IP, max 5 concurrent requests)
Unified error handling and logging with request tracing
Dockerized deployment with environment variable configuration
Simulation mode for development without API costs
Integrated Hugging Face API for production inference

Technical Highlights

Implemented under comfyui-service/ directory to avoid conflicts with other modules
Exposes API documentation at:
- Swagger UI: http://localhost:8001/docs
- ReDoc: http://localhost:8001/redoc
Clear folder structure (api/, utils/, models/, tests/, main.py, Dockerfile)
Designed with microservice principles: single responsibility, independent deployment, safe integration
Rate limits: 15 requests/minute per IP, 10MB upload limit

Validation

✅ Service successfully starts on port 8001
✅ All endpoints tested and responding
✅ Rate limiting and file validation verified
✅ Error handling prevents sensitive information leakage
✅ Docker build and run verified

Next Steps

Connect this microservice with the CerebraUI main backend
Add frontend integration for user-triggered image generation
Extend advanced multimodal and fashion transfer workflows

By submitting this pull request, I confirm that I have read and fully agree to the Contributor License Agreement (CLA), and I am providing my contributions under its terms.

How to Run

# Local
pip install -r requirements.txt
python main.py

# Docker
docker build -t comfyui-service .
docker run -p 8001:8001 -e HUGGINGFACE_API_TOKEN="hf_your_token" comfyui-service

# Docker Compose
docker-compose up



---

<sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/open-webui/pull/17734 **Author:** [@PerryPAN219](https://github.com/PerryPAN219) **Created:** 9/25/2025 **Status:** ❌ Closed **Base:** `main` ← **Head:** `feat/perry-comfyui-deployment` --- ### 📝 Commits (2) - [`3e95e7c`](https://github.com/open-webui/open-webui/commit/3e95e7c40d7039a50462ad56a53f2ec1d9c4f268) Scaffold Setup, setup guide and updated docker-compose configuration: - [`48cde43`](https://github.com/open-webui/open-webui/commit/48cde437701192986baca20d01fa89a52004649b) Add ComfyUI service with image-to-image Fal.ai integration ### 📊 Changes **12 files changed** (+1364 additions, -13 deletions) <details> <summary>View changed files</summary> 📝 `backend/open_webui/config.py` (+13 -0) 📝 `backend/open_webui/env.py` (+1 -0) ➕ `comfyui-service/.gitignore` (+62 -0) ➕ `comfyui-service/Dockerfile` (+35 -0) ➕ `comfyui-service/README.md` (+126 -0) ➕ `comfyui-service/api/__init__.py` (+7 -0) ➕ `comfyui-service/api/routes.py` (+571 -0) ➕ `comfyui-service/docker-compose.yml` (+31 -0) ➕ `comfyui-service/main.py` (+230 -0) ➕ `comfyui-service/requirements.txt` (+9 -0) 📝 `docker-compose.yaml` (+24 -13) ➕ `setupguide.md` (+255 -0) </details> ### 📄 Description ### Summary This PR introduces a new **ComfyUI Microservice** for AI image generation, integrated into the CerebraUI platform. It provides core workflows (text-to-image, image-to-image, multimodal, and fashion transfer) with FastAPI-based endpoints. ### Key Features - Independent microservice at port 8001 - Text-to-image, image-to-image, multimodal, and fashion transfer endpoints - File upload validation (JPEG, PNG, WebP, BMP, TIFF, GIF; max 10MB) - Rate limiting (15 requests/minute per IP, max 5 concurrent requests) - Unified error handling and logging with request tracing - Dockerized deployment with environment variable configuration - Simulation mode for development without API costs - Integrated Hugging Face API for production inference ### Technical Highlights - Implemented under `comfyui-service/` directory to avoid conflicts with other modules - Exposes API documentation at: - Swagger UI: http://localhost:8001/docs - ReDoc: http://localhost:8001/redoc - Clear folder structure (`api/`, `utils/`, `models/`, `tests/`, `main.py`, `Dockerfile`) - Designed with microservice principles: single responsibility, independent deployment, safe integration - Rate limits: 15 requests/minute per IP, 10MB upload limit ### Validation - ✅ Service successfully starts on port 8001 - ✅ All endpoints tested and responding - ✅ Rate limiting and file validation verified - ✅ Error handling prevents sensitive information leakage - ✅ Docker build and run verified ### Next Steps - Connect this microservice with the CerebraUI main backend - Add frontend integration for user-triggered image generation - Extend advanced multimodal and fashion transfer workflows By submitting this pull request, I confirm that I have read and fully agree to the [Contributor License Agreement (CLA)](https://github.com/open-webui/open-webui/blob/main/CONTRIBUTOR_LICENSE_AGREEMENT), and I am providing my contributions under its terms. ### How to Run ```bash # Local pip install -r requirements.txt python main.py # Docker docker build -t comfyui-service . docker run -p 8001:8001 -e HUGGINGFACE_API_TOKEN="hf_your_token" comfyui-service # Docker Compose docker-compose up --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

GiteaMirror added the pull-request label 2025-11-11 19:28:53 -06:00

GiteaMirror closed this issue

2025-11-11 19:28:53 -06:00

GiteaMirror referenced this issue

2026-04-19 22:12:15 -05:00

[GH-ISSUE #11326] feat: RAG Does the text document support custom modes, such as using custom separators #16186

GiteaMirror referenced this issue

2026-04-25 05:37:21 -05:00

[GH-ISSUE #11326] feat: RAG Does the text document support custom modes, such as using custom separators #31715

GiteaMirror referenced this issue

2026-05-05 16:48:45 -05:00

[GH-ISSUE #11326] feat: RAG Does the text document support custom modes, such as using custom separators #54852