---
title: flux1-kontext-dev-fp8
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/flux1-kontext-dev-fp8"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/flux1-kontext-dev-fp8.md"
repository: AI-ModelScope/flux1-kontext-dev-fp8
last_updated: 2025-07-04
license: other
pipeline_tag: image-to-image
tasks:
  - image-to-image
base_model:
  - black-forest-labs/FLUX.1-Kontext-dev
base_model_relation: quantized
parameters: 23.8B
tensor_type:
  - F8_E5M2
  - F8_E4M3
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 4656
stars: 14
tags:
  - image-generation
  - flux
  - diffusion-single-file
---

# flux1-kontext-dev-fp8

> flux1-kontext-dev-fp8 - AI-ModelScope 在 ModelScope 开源的模型。flux1-kontext-dev-fp8

AI-ModelScope/flux1-kontext-dev-fp8 是 ModelScope 魔搭社区上的 23.8B 参数image-to-image模型，采用 other 许可，基于 black-forest-labs/FLUX.1-Kontext-dev 构建。

- **Repository**: AI-ModelScope/flux1-kontext-dev-fp8
- **License**: other
- **Tasks**: image-to-image
- **Parameters**: 23.8B
- **Base model**: black-forest-labs/FLUX.1-Kontext-dev
- **Tags**: image-generation, flux, diffusion-single-file
- **Downloads**: 4656
- **Stars**: 14
- **Last updated**: 2025-07-04

Source: https://www.modelscope.cn/models/AI-ModelScope/flux1-kontext-dev-fp8

---

# flux1-kontext-dev-fp8

FP8-quantized weights for [FLUX.1-Kontext-dev](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev) diffusion models. Supports both E4M3FN and E5M2 formats.

## Model Overview
- **Base Model**: [FLUX.1-Kontext-dev](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev) (diffusion model component)
- **Quantization**: Per-tensor dynamic quantization to FP8 (E4M3FN/E5M2)
- **Size Reduction**: ~40% smaller than original weights
- **Model Scope**: This is **only the diffusion_model** component (not full pipeline), should be placed in ComfyUI's `diffusion_models` directory
- **Compatibility**: 
  - ✅ ComfyUI (with PyTorch 2.4+ and CUDA 12.4+)
  - ❌ Diffusers (currently unsupported)

## Available Files
- `flux1-kontext-dev-fp8-e4m3fn.safetensors` - Balanced performance/accuracy
- `flux1-kontext-dev-fp8-e5m2.safetensors` - Higher throughput on Hopper GPUs

## Usage
1. Move the `.safetensors` file to your ComfyUI `diffusion_models` directory
2. Select fp8 modes in UNet Loader like `fp8_e4m3fn`.

## Known Limitations
1. Not compatible with standard Diffusers pipelines
2. Requires patched PyTorch versions for optimal performance

## License
This model is distributed under the [FLUX.1(dev) Non-Commercial License](https://github.com/black-forest-labs/flux/blob/main/model_licenses/LICENSE-FLUX1-dev). Commercial use prohibited without authorization.

## Citation
```bib
@misc{labs2025flux1kontextflowmatching,
      title={FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space},
      author={Black Forest Labs et al.},
      year={2025},
      eprint={2506.15742},
      archivePrefix={arXiv},
      primaryClass={cs.GR},
      url={https://arxiv.org/abs/2506.15742},
}
```