FLUX.2-dev-Turbo / README.md
kaanakan's picture
Update README.md
9ee51cd verified
---
language:
- en
license: other
license_name: flux-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.2-dev/blob/main/LICENSE.txt
base_model: black-forest-labs/FLUX.2-dev
tags:
- image-generation
- flux
- lora
- distillation
- turbo
pipeline_tag: text-to-image
library_name: diffusers
---
# FLUX.2 [dev] Turbo LoRA
**FLUX.2 [dev] Turbo** is a distilled LoRA adapter for [FLUX.2 [dev]](https://huggingface.co/black-forest-labs/FLUX.2-dev) that enables high-quality image generation in just **8 inference steps**.
![Example Text-to-Image](./example_t2i.png)
---
---
![Example Image Editing](./example_edit.png)
## Key Features
- ⚑ **8-step inference** β€” 6x faster than the base model's typical 50 steps
- 🎨 **Quality preserved** β€” Matches or surpasses the original FLUX.2 [dev] quality
- πŸ”Œ **LoRA adapter** β€” Lightweight, easy to integrate with existing FLUX.2 workflows
- πŸ–ΌοΈ **Multiple modes** β€” Supports both text-to-image and image editing
## Hosted API Endpoints
FLUX.2 [dev] Turbo is available through fal.ai hosted endpoints:
- [Text-to-Image](https://fal.ai/models/fal-ai/flux-2/turbo)
- [Image Editing](https://fal.ai/models/fal-ai/flux-2/turbo/edit)
## ComfyUI
ComfyUI-compatible weights are available in the `comfy/` directory, converted by [ByteZSzn](https://huggingface.co/ByteZSzn/Flux.2-Turbo-ComfyUI).
## Usage
```python
import torch
from diffusers import Flux2Pipeline
# Pre-shifted custom sigmas for 8-step turbo inference
TURBO_SIGMAS = [1.0, 0.6509, 0.4374, 0.2932, 0.1893, 0.1108, 0.0495, 0.00031]
pipe = Flux2Pipeline.from_pretrained(
"black-forest-labs/FLUX.2-dev",
torch_dtype=torch.bfloat16
).to("cuda")
pipe.load_lora_weights(
"fal/FLUX.2-dev-Turbo",
weight_name="flux.2-turbo-lora.safetensors"
)
prompt = "Industrial product shot of a chrome turbocharger with glowing hot exhaust manifold, engraved text 'FLUX.2 [dev] Turbo by fal' on the compressor housing and 'fal' on the turbine wheel, gradient heat glow from orange to electric blue , studio lighting with dramatic shadows, shallow depth of field, engineering blueprint pattern in background."
image = pipe(
prompt=prompt,
sigmas=TURBO_SIGMAS,
guidance_scale=2.5,
height=1024,
width=1024,
num_inference_steps=8,
).images[0]
image.save("output.png")
```
## License
This model inherits the [FLUX [dev] Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.2-dev/blob/main/LICENSE.txt) from the base model.