AIbase
EN
Home
Nunchaku Flux.1 Canny Dev
N

Nunchaku Flux.1 Canny Dev

Developed by mit-han-lab
The Nunchaku quantized version of FLUX.1-Canny-dev, capable of generating images based on text descriptions while following the structure of the given input image.
Image Generation EnglishOpen Source License:Other#Image structure preservation#4-bit quantization inference#Text-guided generation
Downloads 1,817
Release Time : 5/29/2025

Model Overview

This model is a quantized version based on FLUX.1-Canny-dev, focusing on image-to-image generation tasks. It can be optimized for efficient inference while minimizing performance loss.

Model Features

Efficient inference optimization
Optimize the model through quantization technology to achieve efficient inference while minimizing performance loss.
Image structure preservation
Capable of generating images based on text descriptions while strictly following the structure of the input image.
Multi-hardware support
Provide quantized versions suitable for different GPU architectures, including non-Blackwell GPUs and Blackwell GPUs.

Model Capabilities

Text-to-image generation
Image structure preservation
Efficient inference

Use Cases

Creative design
Image style conversion
Convert the input image into an image of a specific style based on text descriptions.
Content generation
Text-based image generation
Generate new images that conform to the structure of the input image based on text prompts.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
EnglishįŽ€äŊ“中文įšéĢ”中文ãĢãģんご
Š 2025AIbase