README.md

---
license: other
language:
- en
base_model:
- black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
tags:
- diffusers
- controlnet
- Flux
- image-generation
---

# Description
This repository provides a Diffusers version of FLUX.1-dev Depth ControlNet checkpoint by Xlabs AI, [original repo](https://huggingface.co/XLabs-AI/flux-controlnet-depth-v3). 

![Example Picture 1](depth_result.png?raw=true)

# How to use
This model can be used directly with the diffusers library

```
import torch
from diffusers.utils import load_image
from diffusers import FluxControlNetModel
from diffusers.pipelines import FluxControlNetPipeline
from PIL import Image
import numpy as np

generator = torch.Generator(device="cuda").manual_seed(87544357)

controlnet = FluxControlNetModel.from_pretrained(
  "Xlabs-AI/flux-controlnet-depth-diffusers",
  torch_dtype=torch.bfloat16,
  use_safetensors=True,
)
pipe = FluxControlNetPipeline.from_pretrained(
  "black-forest-labs/FLUX.1-dev",
  controlnet=controlnet,
  torch_dtype=torch.bfloat16
)
pipe.to("cuda")

control_image = load_image("https://huggingface.co/Xlabs-AI/flux-controlnet-depth-diffusers/resolve/main/depth_example.png")
prompt = "photo of fashion woman in the street"

image = pipe(
    prompt,
    control_image=control_image,
    controlnet_conditioning_scale=0.7,
    num_inference_steps=25,
    guidance_scale=3.5,
    height=768,
    width=1024,
    generator=generator,
    num_images_per_prompt=1,
).images[0]

image.save("output_test_controlnet.png")
```

## License

Our weights fall under the [FLUX.1 [dev]](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md) Non-Commercial License<br/>