why my pose does not work？
#28
by
YearW
- opened
how to use pose to control image
I am just doing this
prompt = 'A fashion model'
control_image_pose = load_image("pose_images/standing_19.png")
control_mode_pose = 4
width, height = 720, 720
image = pipe(
prompt,
control_image=[control_image_pose],
control_mode=[control_mode_pose],
width=width,
height=height,
controlnet_conditioning_scale=[0.6],
num_inference_steps=24,
guidance_scale=3.5,
generator=torch.manual_seed(1),
).images[0]