T

jasonandjason.mei 2be7d1e881 add gpt-image,qwen,nano banana (#5 )

* add gitignore

* add video api

* fix: export to video

* fix

* fix

* fix

* fix

* fix

* add i2v

* fix

* fix

* add openai

* fix: add base url

* change default models

* fix: add base url

* add v1

* fix models

* fix models

* fix models

* fix models

* fix models

* fix bug

* fix

* try to fix

* use IO.STRING test

* image fix

* add chat content

* add files

* fix optional

* fix file read

* fix file read

* change name

* add get models

* add unused apikey

* change model sort

* fix IMAGE_LIST

* fix: change to image

* add model cache

* remove json_object

* change max_tokens to 65536

* change max_tokens to 6000

* add pic model

* fix gpt-image-1

* fix gpt-image-1

* fix gpt

* fix gpt

* fix gpt

* fix gpt

* add gpt edit

* fix gpt edit

* update project.toml

---------

Co-authored-by: jason.mei <jason.mei@ucloud.cn>

2025-09-23 11:26:19 +08:00

.github/workflows

comfyui git action init

2025-07-22 17:32:22 +08:00

assets

add more workflow examples.

2025-07-11 15:46:38 +08:00

add gpt-image,qwen,nano banana (#5 )

2025-09-23 11:26:19 +08:00

__init__.py

add video async api

2025-09-09 13:52:07 +08:00

.gitignore

add video async api

2025-09-09 13:52:07 +08:00

config.ini

Initial commit

2025-07-11 14:57:59 +08:00

pyproject.toml

add gpt-image,qwen,nano banana (#5 )

2025-09-23 11:26:19 +08:00

README.md

Better Readme

2025-08-13 14:27:43 +08:00

requirements.txt

support text generation

2025-09-15 15:31:26 +08:00

README.md

UCloud ModelVerse API for ComfyUI

This plugin provides seamless integration with UCloud's ModelVerse API, enabling you to use powerful AI models directly within ComfyUI for image generation and editing tasks.

Quick Start

Installation

Install via Custom Node Manager (Recommended)
- Open ComfyUI
- Go to Manager → Custom Nodes Manager
- Search for "ComfyUl-UCloud"
- Click Install
- Restart ComfyUI
Configure API Key
- Get your API key: Console En, Console Zh
- Add your UCloud ModelVerse API key in the Modelverse Client node
- Alternatively, create a config.ini file with MODELVERSE_API_KEY=your_api_key

Basic Usage

Add a Modelverse Client node to your workflow
Choose your desired model from the supported models below
Connect the appropriate input/output nodes
Run your workflow

Supported Models

Our plugin supports the following models, each optimized for specific use cases:

Flux Dev - Foundation model with strong stylization capabilities
Flux Kontext Pro Text2Image - Specialized for text-to-image generation
Flux Kontext Pro - Expert single image editing and enhancement
Flux Kontext Pro (Multi-inputs) - Batch processing for multiple images
Flux Kontext Max Text2Image - Premium text-to-image generation with highest quality
Flux Kontext Max - Flagship single image editing with advanced features
Flux Kontext Max (Multi-inputs) - Most powerful multi-image processing
Step1X-Edit - Precision local editing and inpainting

Note: (Multi-inputs) models use the same node interface as their single-input counterparts. Check the example workflows below for implementation details.

Example Workflows

Build your own workflow with Modelverse nodes. You can check the following images, drag them into ComfyUI GUI and autoload example workflows.

Flux Dev	Flux Kontext Pro	Flux Kontext Max (Multi-inputs)

In case the above images does not work for you, check the screenshot below:

Text-to-Image with Flux Dev

Single image editting with Flux Kontext Pro

Multi image editting with Flux Kontext Max