mirror of
https://www.modelscope.cn/alimama-creative/FLUX.1-Turbo-Alpha.git
synced 2026-04-02 13:32:53 +08:00
82 lines
2.9 KiB
Markdown
82 lines
2.9 KiB
Markdown
---
|
|
license: other
|
|
license_name: flux-1-dev-non-commercial-license
|
|
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
|
|
language:
|
|
- en
|
|
base_model: black-forest-labs/FLUX.1-dev
|
|
library_name: diffusers
|
|
tags:
|
|
- Text-to-Image
|
|
- FLUX
|
|
- Stable Diffusion
|
|
pipeline_tag: text-to-image
|
|
---
|
|
|
|
<div style="display: flex; justify-content: center; align-items: center;">
|
|
<img src="./images/images_alibaba.png" alt="alibaba" style="width: 20%; height: auto; margin-right: 5%;">
|
|
<img src="./images/images_alimama.png" alt="alimama" style="width: 20%; height: auto;">
|
|
</div>
|
|
|
|
[中文版Readme](./README_ZH.md)
|
|
|
|
This repository provides a 8-step distilled lora for [FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) model released by AlimamaCreative Team.
|
|
|
|
# Description
|
|
This checkpoint is a 8-step distilled Lora, trained based on FLUX.1-dev model. We use a multi-head discriminator to improve the distill quality. Our model can be used for T2I, inpainting controlnet and other FLUX related models. The recommended guidance_scale=3.5 and lora_scale=1. Our Lower steps version will release later.
|
|
|
|
- Text-to-Image.
|
|
|
|
|
|
|
|
- With [alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta](https://huggingface.co/alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta). Our distilled lora can be well adapted to the Inpainting controlnet, and the accelerated generated effect can follow the original output well.
|
|
|
|
|
|
|
|
# How to use
|
|
## diffusers
|
|
This model can be used ditrectly with diffusers
|
|
|
|
```python
|
|
import torch
|
|
from diffusers.pipelines import FluxPipeline
|
|
|
|
model_id = "black-forest-labs/FLUX.1-dev"
|
|
adapter_id = "alimama-creative/FLUX.1-Turbo-Alpha"
|
|
|
|
pipe = FluxPipeline.from_pretrained(
|
|
model_id,
|
|
torch_dtype=torch.bfloat16
|
|
)
|
|
pipe.to("cuda")
|
|
|
|
pipe.load_lora_weights(adapter_id)
|
|
pipe.fuse_lora()
|
|
|
|
prompt = "A DSLR photo of a shiny VW van that has a cityscape painted on it. A smiling sloth stands on grass in front of the van and is wearing a leather jacket, a cowboy hat, a kilt and a bowtie. The sloth is holding a quarterstaff and a big book."
|
|
image = pipe(
|
|
prompt=prompt,
|
|
guidance_scale=3.5,
|
|
height=1024,
|
|
width=1024,
|
|
num_inference_steps=8,
|
|
max_sequence_length=512).images[0]
|
|
```
|
|
|
|
## comfyui
|
|
|
|
- T2I turbo workflow: [click here](./workflows/t2I_flux_turbo.json)
|
|
- Inpainting controlnet turbo workflow: [click here](./workflows/alimama_flux_inpainting_turbo_8step.json)
|
|
|
|
|
|
# Training Details
|
|
|
|
The model is trained on 1M open source and internal sources images, with the aesthetic 6.3+ and resolution greater than 800. We use adversarial training to improve the quality. Our method fix the original FLUX.1-dev transformer as the discriminator backbone, and add multi heads to every transformer layer. We fix the guidance scale as 3.5 during training, and use the time shift as 3.
|
|
|
|
Mixed precision: bf16
|
|
|
|
Learning rate: 2e-5
|
|
|
|
Batch size: 64
|
|
|
|
Image size: 1024x1024 |