Open-source flux-ip-adapter-v2 model - Achieve efficient image-to-image conversion for free

Flux Ip Adapter V2

Developed by XLabs-AI

IP adapter checkpoint based on the FLUX.1-dev model for image-to-image conversion tasks

Image Generation EnglishOpen Source License:Apache-2.0 #Image Style Transfer #High-Resolution Adaptation #Anime Style Generation

Downloads 42.49k

Release Time : 10/23/2024

Model Overview

This model is an image-to-image adapter capable of high-resolution image processing while maintaining aspect ratios, supporting 512x512 and 1024x1024 resolutions.

Model Features

High-Resolution Support

Supports 512x512 and 1024x1024 resolutions while preserving the original image's aspect ratio

ComfyUI Integration

Provides custom ComfyUI nodes for easy integration into workflows

Multi-Step Training

Trained for 150,000 steps at 512x512 resolution and 350,000 steps at 1024x1024 resolution

Model Capabilities

Image Style Transfer

Image Content Preservation

High-Resolution Image Processing

Use Cases

Creative Design

Anime Style Conversion

Convert ordinary images into anime style

As shown in the example Mona anime workflow

Artistic Creation

Generate new artworks in different styles based on input images

As demonstrated by various IP adapter effects in the examples

🚀 IP-Adapter Checkpoint for FLUX.1-dev

This repository offers an IP-Adapter checkpoint for the FLUX.1-dev model developed by Black Forest Labs. It aims to enhance the image - to - image capabilities of the base model.

🚀 Quick Start

To try our models, you have 2 options:

Use main.py from our official repo.
Use our custom nodes for ComfyUI and test it with provided workflows (check out folder /workflows).

✨ Features

The IP adapter is trained on a resolution of 512x512 for 150k steps and 1024x1024 for 350k steps while maintaining the aspect ratio.
We release the v2 version - which can be used directly in ComfyUI!

📦 Installation

Instruction for ComfyUI

Go to ComfyUI/custom_nodes.
Clone x-flux-comfyui. The path should be ComfyUI/custom_nodes/x-flux-comfyui/*, where * represents all the files in this repo.
Go to ComfyUI/custom_nodes/x-flux-comfyui/ and run python setup.py.
Update x-flux-comfy with git pull or reinstall it.
Download Clip - L model.safetensors from OpenAI VIT CLIP large, and put it to ComfyUI/models/clip_vision/*.
Download our IPAdapter from huggingface, and put it to ComfyUI/models/xlabs/ipadapters/*.
Use Flux Load IPAdapter and Apply Flux IPAdapter nodes, choose the right CLIP model and enjoy your generations.
You can find an example workflow in the workflows folder in this repo.

💻 Usage Examples

Basic Usage

You can use the following steps to start using the model:

Follow the installation steps for ComfyUI as described above.
Navigate to the appropriate nodes in ComfyUI and start generating images.

Advanced Usage

If you want to fine - tune the results, you can try to set and play with the ip strength parameter.

📚 Documentation

See our github for comfy ui workflows.
See examples of our models results below. Also, some generation results with input images are provided in "Files and versions".

Limitations

The IP Adapter is currently in beta. We do not guarantee that you will get a good result right away, it may take more attempts to get a result.

📄 License

Our weights fall under the FLUX.1 [dev] Non - Commercial License.

Property	Details
Model Type	IP-Adapter checkpoint for FLUX.1-dev
Training Data	CaptionEmporium/coyo-hd-11m-llavanext, CortexLM/midjourney-v6
Base Model	black-forest-labs/FLUX.1-dev
Pipeline Tag	image-to-image
Library Name	diffusers

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご