README.md

metadata

license: other
license_name: flux-1-dev-non-commercial-license
license_link: LICENSE

FLUX Model Merge: Detail Enhancement and Acceleration

This repository contains a merge of two FLUX models, with detail enhancement and acceleration techniques applied. The result consists of six files in total, divided into three quantized GGUF (Q8_0) and three optimized SAFETensors format (fp8_34m3fn_fast).

Files:

1. GGUF Quantized Models (Q8_0):

   • Model 1
   • Model 2
   • Model 3

2. SAFETensors Format (fp8_34m3fn_fast):

   • Hyper-FLUX.1-dev-16steps
   • Hyper-FLUX.1-dev-8steps
   • FLUX.1-Turbo-Alpha

Detail Enhancement Models Used:

1. FLUX [pro] 1.1 Style LORA - Extreme Detailer for FLUX.1-dev (Weight: 0.5) (Model Link)
2. Best of Flux: Style Enhancing LoRA (Weight: 0.25) (Model Link)

Optimization Credits:

• ByteDance, a leading AI technology company, optimized the following models:

  • Hyper-FLUX.1-dev-16steps
  • Hyper-FLUX.1-dev-8steps

• Alimama Creative, a renowned NLP innovator, optimized the following model:

  • FLUX.1-Turbo-Alpha

Attribution and Licensing Notice:

The FLUX.1 [dev] Model is licensed by Black Forest Labs, Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs, Inc.

Our model weights are released under the FLUX.1 [dev] Non-Commercial License (https://huggingface.co/mdmachine/flux.1-lite-8B-alpha-Hyper-8.Steps-Detail.Plus-fp8_e4m3fn_fast/blob/main/LICENSE.md).

This merge combines the strengths of these models, applying detail enhancement and acceleration techniques to create a unique and powerful AI model. We hope this contributes positively to the development of the NLP community!