BRIA-2.3-ControlNet-Depth

Ejemplo de código usando Diffusers

pip install diffusers

from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline
import torch
from transformers import DPTFeatureExtractor, DPTForDepthEstimation
depth_estimator = DPTForDepthEstimation.from_pretrained("Intel/dpt-hybrid-midas").to("cuda")
feature_extractor = DPTFeatureExtractor.from_pretrained("Intel/dpt-hybrid-midas")

def get_depth_map(image):
  image = feature_extractor(images=image, return_tensors="pt").pixel_values.to("cuda")
  with torch.no_grad(), torch.autocast("cuda"):
    depth_map = depth_estimator(image).predicted_depth
    image = transforms.functional.center_crop(image, min(image.shape[-2:]))
    depth_map = torch.nn.functional.interpolate(
      depth_map.unsqueeze(1),
      size=(1024, 1024),
      mode="bicubic",
      align_corners=False,
    )
    depth_min = torch.amin(depth_map, dim=[1, 2, 3], keepdim=True)
    depth_max = torch.amax(depth_map, dim=[1, 2, 3], keepdim=True)
    depth_map = (depth_map - depth_min) / (depth_max - depth_min)
    image = torch.cat([depth_map] * 3, dim=1)
    image = image.permute(0, 2, 3, 1).cpu().numpy()[0]
    image = Image.fromarray((image * 255.0).clip(0, 255).astype(np.uint8))
    return image

controlnet = ControlNetModel.from_pretrained(
  "briaai/BRIA-2.3-ControlNet-Depth",
  torch_dtype=torch.float16
)

pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
  "briaai/BRIA-2.3",
  controlnet=controlnet,
  torch_dtype=torch.float16,
)
pipe.to("cuda")

prompt = "A portrait of a Beautiful and playful ethereal singer, golden designs, highly detailed, blurry background"
negative_prompt = "Logo,Watermark,Text,Ugly,Morbid,Extra fingers,Poorly drawn hands,Mutation,Blurry,Extra limbs,Gross proportions,Missing arms,Mutated hands,Long neck,Duplicate,Mutilated,Mutilated hands,Poorly drawn face,Deformed,Bad anatomy,Cloned face,Malformed limbs,Missing legs,Too many fingers"

# Calculate Depth image
input_image = cv2.imread('pics/singer.png')
depth_image = get_depth_map(input_image)
image = pipe(prompt=prompt, negative_prompt=negative_prompt, image=depth_image, controlnet_conditioning_scale=1.0, height=1024, width=1024).images[0]