Several fixes to Flux ControlNet pipelines by vladmandic · Pull Request #9472 · huggingface/diffusers (original) (raw)

Facing issues when using 'FluxMultiControlNetModel'.

A call to a pipeline leads to the following error: 'FluxMultiControlNetModel' object has no attribute 'config'

For those stumbling upon this message.

A simple set of the config property does the trick:

base_model = 'black-forest-labs/FLUX.1-dev'
controlnet_model_union = 'InstantX/FLUX.1-dev-Controlnet-Union'

controlnet_union = FluxControlNetModel.from_pretrained(controlnet_model_union, torch_dtype=torch.bfloat16)
controlnet = FluxMultiControlNetModel([controlnet_union]) # we always recommend loading via FluxMultiControlNetModel

# Trick
controlnet.config = controlnet_union.config

pipe = FluxControlNetPipeline.from_pretrained(base_model, controlnet=controlnet, torch_dtype=torch.bfloat16)
pipe.to("cuda")

prompt = 'A bohemian-style female travel blogger with sun-kissed skin and messy beach waves.'
control_image_depth = load_image("https://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Union/resolve/main/images/depth.jpg")
control_mode_depth = 2

control_image_canny = load_image("https://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Union/resolve/main/images/canny.jpg")
control_mode_canny = 0

width, height = control_image.size

image = pipe(
    prompt, 
    control_image=[control_image_depth, control_image_canny],
    control_mode=[control_mode_depth, control_mode_canny],
    width=width,
    height=height,
    controlnet_conditioning_scale=[0.2, 0.4],
    num_inference_steps=24, 
    guidance_scale=3.5,
    generator=torch.manual_seed(42),
).images[0]