svjack's picture
Update canny_app.py
8e3b30d verified
import random
import torch
import cv2
import gradio as gr
import numpy as np
from huggingface_hub import snapshot_download
from transformers import CLIPVisionModelWithProjection, CLIPImageProcessor
from diffusers.utils import load_image
from kolors.pipelines.pipeline_controlnet_xl_kolors_img2img import StableDiffusionXLControlNetImg2ImgPipeline
from kolors.models.modeling_chatglm import ChatGLMModel
from kolors.models.tokenization_chatglm import ChatGLMTokenizer
from kolors.models.controlnet import ControlNetModel
from diffusers import AutoencoderKL
from kolors.models.unet_2d_condition import UNet2DConditionModel
from diffusers import EulerDiscreteScheduler
from PIL import Image
from annotator.util import resize_image, HWC3
device = "cuda"
ckpt_dir = snapshot_download(repo_id="Kwai-Kolors/Kolors")
ckpt_dir_ipa = snapshot_download(repo_id="Kwai-Kolors/Kolors-IP-Adapter-Plus")
ckpt_dir_canny = snapshot_download(repo_id="Kwai-Kolors/Kolors-ControlNet-Canny")
text_encoder = ChatGLMModel.from_pretrained(f'{ckpt_dir}/text_encoder', torch_dtype=torch.float16).half().to(device)
tokenizer = ChatGLMTokenizer.from_pretrained(f'{ckpt_dir}/text_encoder')
vae = AutoencoderKL.from_pretrained(f"{ckpt_dir}/vae", revision=None).half().to(device)
scheduler = EulerDiscreteScheduler.from_pretrained(f"{ckpt_dir}/scheduler")
unet = UNet2DConditionModel.from_pretrained(f"{ckpt_dir}/unet", revision=None).half().to(device)
controlnet_canny = ControlNetModel.from_pretrained(f"{ckpt_dir_canny}", revision=None).half().to(device)
image_encoder = CLIPVisionModelWithProjection.from_pretrained(f'{ckpt_dir_ipa}/image_encoder', ignore_mismatched_sizes=True).to(dtype=torch.float16, device=device)
ip_img_size = 336
clip_image_processor = CLIPImageProcessor(size=ip_img_size, crop_size=ip_img_size)
pipe_canny = StableDiffusionXLControlNetImg2ImgPipeline(
vae=vae,
controlnet=controlnet_canny,
text_encoder=text_encoder,
tokenizer=tokenizer,
unet=unet,
scheduler=scheduler,
image_encoder=image_encoder,
feature_extractor=clip_image_processor,
force_zeros_for_empty_prompt=False
)
pipe_canny.load_ip_adapter(f'{ckpt_dir_ipa}', subfolder="", weight_name=["ip_adapter_plus_general.bin"])
def process_canny_condition(image, canny_threods=[100, 200]):
np_image = image.copy()
np_image = cv2.Canny(np_image, canny_threods[0], canny_threods[1])
np_image = np_image[:, :, None]
np_image = np.concatenate([np_image, np_image, np_image], axis=2)
np_image = HWC3(np_image)
return Image.fromarray(np_image)
MAX_SEED = np.iinfo(np.int32).max
#MAX_IMAGE_SIZE = 1024
MAX_IMAGE_SIZE = 512
def infer_canny(prompt,
image=None,
ipa_img=None,
negative_prompt="nsfw,脸部阴影,低分辨率,糟糕的解剖结构、糟糕的手,缺失手指、质量最差、低质量、jpeg伪影、模糊、糟糕,黑脸,霓虹灯",
seed=66,
randomize_seed=False,
guidance_scale=5.0,
num_inference_steps=50,
controlnet_conditioning_scale=0.5,
control_guidance_end=0.9,
strength=1.0,
ip_scale=0.5,
):
if randomize_seed:
seed = random.randint(0, MAX_SEED)
generator = torch.Generator().manual_seed(seed)
init_image = resize_image(image, MAX_IMAGE_SIZE)
pipe = pipe_canny.to("cuda")
pipe.set_ip_adapter_scale([ip_scale])
condi_img = process_canny_condition(np.array(init_image))
image = pipe(
prompt=prompt,
image=init_image,
controlnet_conditioning_scale=controlnet_conditioning_scale,
control_guidance_end=control_guidance_end,
ip_adapter_image=[ipa_img],
strength=strength,
control_image=condi_img,
negative_prompt=negative_prompt,
num_inference_steps=num_inference_steps,
guidance_scale=guidance_scale,
num_images_per_prompt=1,
generator=generator,
).images[0]
return [condi_img, image], seed
canny_examples = [
["一个红色头发的女孩,唯美风景,清新明亮,斑驳的光影,最好的质量,超细节,8K画质",
"image/woman_2.png", "image/2.png"],
]
css = """
#col-left {
margin: 0 auto;
max-width: 600px;
}
#col-right {
margin: 0 auto;
max-width: 750px;
}
#button {
color: blue;
}
"""
def load_description(fp):
with open(fp, 'r', encoding='utf-8') as f:
content = f.read()
return content
with gr.Blocks(css=css) as CannyApp:
gr.HTML(load_description("assets/title.md"))
with gr.Row():
with gr.Column(elem_id="col-left"):
with gr.Row():
prompt = gr.Textbox(
label="Prompt",
placeholder="Enter your prompt",
lines=2
)
with gr.Row():
image = gr.Image(label="Image", type="pil")
ipa_image = gr.Image(label="IP-Adapter-Image", type="pil")
with gr.Accordion("Advanced Settings", open=False):
negative_prompt = gr.Textbox(
label="Negative prompt",
placeholder="Enter a negative prompt",
visible=True,
value="nsfw,脸部阴影,低分辨率,糟糕的解剖结构、糟糕的手,缺失手指、质量最差、低质量、jpeg伪影、模糊、糟糕,黑脸,霓虹灯"
)
seed = gr.Slider(
label="Seed",
minimum=0,
maximum=MAX_SEED,
step=1,
value=0,
)
randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
with gr.Row():
guidance_scale = gr.Slider(
label="Guidance scale",
minimum=0.0,
maximum=10.0,
step=0.1,
value=5.0,
)
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=10,
maximum=50,
step=1,
value=30,
)
with gr.Row():
controlnet_conditioning_scale = gr.Slider(
label="Controlnet Conditioning Scale",
minimum=0.0,
maximum=1.0,
step=0.1,
value=0.5,
)
control_guidance_end = gr.Slider(
label="Control Guidance End",
minimum=0.0,
maximum=1.0,
step=0.1,
value=0.9,
)
with gr.Row():
strength = gr.Slider(
label="Strength",
minimum=0.0,
maximum=1.0,
step=0.1,
value=1.0,
)
ip_scale = gr.Slider(
label="IP_Scale",
minimum=0.0,
maximum=1.0,
step=0.1,
value=0.5,
)
with gr.Row():
canny_button = gr.Button("Canny", elem_id="button")
with gr.Column(elem_id="col-right"):
result = gr.Gallery(label="Result", show_label=False, columns=2)
seed_used = gr.Number(label="Seed Used")
with gr.Row():
gr.Examples(
fn=infer_canny,
examples=canny_examples,
inputs=[prompt, image, ipa_image],
outputs=[result, seed_used],
label="Canny"
)
canny_button.click(
fn=infer_canny,
inputs=[prompt, image, ipa_image, negative_prompt, seed, randomize_seed, guidance_scale, num_inference_steps, controlnet_conditioning_scale, control_guidance_end, strength, ip_scale],
outputs=[result, seed_used]
)
CannyApp.queue().launch(debug=True, share=True)