---
title: FLUX.2-dev-Turbo
canonical_url: "https://www.modelscope.cn/models/fal/FLUX.2-dev-Turbo"
md_url: "https://www.modelscope.cn/models/fal/FLUX.2-dev-Turbo.md"
repository: fal/FLUX.2-dev-Turbo
last_updated: 2026-06-16
license: other
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - black-forest-labs/FLUX.2-dev
base_model_relation: adapter
parameters: 2.8B
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - safetensors
frameworks:
  - pytorch
language:
  - en
supports_inference: img2img
downloads: 1602
stars: 9
tags:
  - image-generation
  - flux
  - lora
  - distillation
  - turbo
---

# FLUX.2-dev-Turbo

> FLUX.2-dev-Turbo - fal 在 ModelScope 开源的模型。FLUX.2 [dev] Turbo LoRA

fal/FLUX.2-dev-Turbo 是 ModelScope 魔搭社区上的 2.8B 参数text-to-image-synthesis模型，采用 other 许可，基于 black-forest-labs/FLUX.2-dev 构建，并支持在线推理（img2img）。

- **Repository**: fal/FLUX.2-dev-Turbo
- **License**: other
- **Tasks**: text-to-image-synthesis
- **Parameters**: 2.8B
- **Base model**: black-forest-labs/FLUX.2-dev
- **Online inference**: img2img
- **Tags**: image-generation, flux, lora, distillation, turbo
- **Downloads**: 1602
- **Stars**: 9
- **Last updated**: 2026-06-16

Source: https://www.modelscope.cn/models/fal/FLUX.2-dev-Turbo

---

# 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** — 6x faster than the base model's typical 50 steps
- 🎨 **Quality preserved** — Matches or surpasses the original FLUX.2 [dev] quality
- 🔌 **LoRA adapter** — Lightweight, easy to integrate with existing FLUX.2 workflows
- 🖼️ **Multiple modes** — 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.