FLUX.1-dev Controlnet
We have completed the training of the first version.
The training was conducted with a total pixel count of 1024*1024
at multi-scale.
We trained for 30k steps using a batch size of 8*8.
![](/InstantX/FLUX.1-dev-Controlnet-Canny/resolve/main/images/image_demo.jpg)
![](/InstantX/FLUX.1-dev-Controlnet-Canny/resolve/main/images/image_demo_weight.png)
Diffusers version:
pip install -U diffusers
Demo
import torch
from diffusers.utils import load_image
from diffusers.pipelines.flux.pipeline_flux_controlnet import FluxControlNetPipeline
from diffusers.models.controlnet_flux import FluxControlNetModel
base_model = 'black-forest-labs/FLUX.1-dev'
controlnet_model = 'InstantX/FLUX.1-dev-Controlnet-Canny'
controlnet = FluxControlNetModel.from_pretrained(controlnet_model, torch_dtype=torch.bfloat16)
pipe = FluxControlNetPipeline.from_pretrained(base_model, controlnet=controlnet, torch_dtype=torch.bfloat16)
pipe.to("cuda")
control_image = load_image("https://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Canny/resolve/main/canny.jpg")
prompt = "A girl in city, 25 years old, cool, futuristic"
image = pipe(
prompt,
control_image=control_image,
controlnet_conditioning_scale=0.6,
num_inference_steps=28,
guidance_scale=3.5,
).images[0]
image.save("image.jpg")
- Downloads last month
- 1,973
Model tree for InstantX/FLUX.1-dev-Controlnet-Canny
Base model
black-forest-labs/FLUX.1-dev
Finetuned
this model