Kolors-Controlnet_and_IPA / switch_app_multi_download.py
svjack's picture
Create switch_app_multi_download.py
ad0ab61 verified
import os
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.midas import MidasDetector
from annotator.dwpose import DWposeDetector
from annotator.util import resize_image, HWC3
from zipfile import ZipFile
from uuid import uuid1
from PIL import Image
device = "cuda"
ckpt_dir = snapshot_download(repo_id="Kwai-Kolors/Kolors")
ckpt_dir_depth = snapshot_download(repo_id="Kwai-Kolors/Kolors-ControlNet-Depth")
ckpt_dir_canny = snapshot_download(repo_id="Kwai-Kolors/Kolors-ControlNet-Canny")
ckpt_dir_ipa = snapshot_download(repo_id="Kwai-Kolors/Kolors-IP-Adapter-Plus")
ckpt_dir_pose = snapshot_download(repo_id="Kwai-Kolors/Kolors-ControlNet-Pose")
'''
ckpt_dir = "Kolors"
ckpt_dir_depth = "Kolors-ControlNet-Depth"
ckpt_dir_canny = "Kolors-ControlNet-Canny"
ckpt_dir_ipa = "Kolors-IP-Adapter-Plus"
ckpt_dir_pose = "Kolors-ControlNet-Pose"
'''
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)
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)
model_midas = MidasDetector()
model_dwpose = DWposeDetector()
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 512
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)
def process_depth_condition_midas(img, res=1024):
h, w, _ = img.shape
img = resize_image(HWC3(img), res)
result = HWC3(model_midas(img))
result = cv2.resize(result, (w, h))
return Image.fromarray(result)
def process_dwpose_condition(image, res=1024):
h, w, _ = image.shape
img = resize_image(HWC3(image), res)
out_res, out_img = model_dwpose(image)
result = HWC3(out_img)
result = cv2.resize(result, (w, h))
return Image.fromarray(result)
def infer_canny(prompt,
image=None,
ipa_img=None,
negative_prompt="nsfw๏ผŒ่„ธ้ƒจ้˜ดๅฝฑ๏ผŒไฝŽๅˆ†่พจ็Ž‡๏ผŒ็ณŸ็ณ•็š„่งฃๅ‰–็ป“ๆž„ใ€็ณŸ็ณ•็š„ๆ‰‹๏ผŒ็ผบๅคฑๆ‰‹ๆŒ‡ใ€่ดจ้‡ๆœ€ๅทฎใ€ไฝŽ่ดจ้‡ใ€jpegไผชๅฝฑใ€ๆจก็ณŠใ€็ณŸ็ณ•๏ผŒ้ป‘่„ธ๏ผŒ้œ“่™น็ฏ",
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,
num_images=1):
if randomize_seed:
seed = random.randint(0, MAX_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))
images = []
for i in range(num_images):
generator = torch.Generator().manual_seed(seed + i)
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]
images.append(image)
return [condi_img] + images, seed
def infer_depth(prompt,
image=None,
ipa_img=None,
negative_prompt="nsfw๏ผŒ่„ธ้ƒจ้˜ดๅฝฑ๏ผŒไฝŽๅˆ†่พจ็Ž‡๏ผŒ็ณŸ็ณ•็š„่งฃๅ‰–็ป“ๆž„ใ€็ณŸ็ณ•็š„ๆ‰‹๏ผŒ็ผบๅคฑๆ‰‹ๆŒ‡ใ€่ดจ้‡ๆœ€ๅทฎใ€ไฝŽ่ดจ้‡ใ€jpegไผชๅฝฑใ€ๆจก็ณŠใ€็ณŸ็ณ•๏ผŒ้ป‘่„ธ๏ผŒ้œ“่™น็ฏ",
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,
num_images=1):
if randomize_seed:
seed = random.randint(0, MAX_SEED)
init_image = resize_image(image, MAX_IMAGE_SIZE)
pipe = pipe_depth.to("cuda")
pipe.set_ip_adapter_scale([ip_scale])
condi_img = process_depth_condition_midas(np.array(init_image), MAX_IMAGE_SIZE)
images = []
for i in range(num_images):
generator = torch.Generator().manual_seed(seed + i)
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]
images.append(image)
return [condi_img] + images, seed
def infer_pose(prompt,
image=None,
ipa_img=None,
negative_prompt="nsfw๏ผŒ่„ธ้ƒจ้˜ดๅฝฑ๏ผŒไฝŽๅˆ†่พจ็Ž‡๏ผŒjpegไผชๅฝฑใ€ๆจก็ณŠใ€็ณŸ็ณ•๏ผŒ้ป‘่„ธ๏ผŒ้œ“่™น็ฏ",
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,
num_images=1):
if randomize_seed:
seed = random.randint(0, MAX_SEED)
init_image = resize_image(image, MAX_IMAGE_SIZE)
pipe = pipe_pose.to("cuda")
pipe.set_ip_adapter_scale([ip_scale])
condi_img = process_dwpose_condition(np.array(init_image), MAX_IMAGE_SIZE)
images = []
for i in range(num_images):
generator = torch.Generator().manual_seed(seed + i)
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]
images.append(image)
return [condi_img] + images, seed
canny_examples = [
["ไธ€ไธช็บข่‰ฒๅคดๅ‘็š„ๅฅณๅญฉ๏ผŒๅ”ฏ็พŽ้ฃŽๆ™ฏ๏ผŒๆธ…ๆ–ฐๆ˜Žไบฎ๏ผŒๆ–‘้ฉณ็š„ๅ…‰ๅฝฑ๏ผŒๆœ€ๅฅฝ็š„่ดจ้‡๏ผŒ่ถ…็ป†่Š‚๏ผŒ8K็”ป่ดจ",
"image/woman_2.png", "image/2.png", 3],
]
depth_examples = [
["ไธ€ไธชๆผ‚ไบฎ็š„ๅฅณๅญฉ๏ผŒๆœ€ๅฅฝ็š„่ดจ้‡๏ผŒ่ถ…็ป†่Š‚๏ผŒ8K็”ป่ดจ",
"image/1.png", "image/woman_1.png", 3],
]
pose_examples = [
["ไธ€ไฝ็ฉฟ็€็ดซ่‰ฒๆณกๆณก่ข–่ฟž่กฃ่ฃ™ใ€ๆˆด็€็š‡ๅ† ๅ’Œ็™ฝ่‰ฒ่•พไธๆ‰‹ๅฅ—็š„ๅฅณๅญฉ๏ผŒ่ถ…้ซ˜ๅˆ†่พจ็Ž‡๏ผŒๆœ€ไฝณๅ“่ดจ๏ผŒ8k็”ป่ดจ",
"image/woman_3.png", "image/woman_4.png", 3],
]
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
def clear_resources():
global pipe_canny, pipe_depth, pipe_pose
if 'pipe_canny' in globals():
del pipe_canny
if 'pipe_depth' in globals():
del pipe_depth
if 'pipe_pose' in globals():
del pipe_pose
torch.cuda.empty_cache()
def load_canny_pipeline():
global pipe_canny
controlnet_canny = ControlNetModel.from_pretrained(f"{ckpt_dir_canny}", revision=None).half().to(device)
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 load_depth_pipeline():
global pipe_depth
controlnet_depth = ControlNetModel.from_pretrained(f"{ckpt_dir_depth}", revision=None).half().to(device)
pipe_depth = StableDiffusionXLControlNetImg2ImgPipeline(
vae=vae,
controlnet=controlnet_depth,
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_depth.load_ip_adapter(f'{ckpt_dir_ipa}', subfolder="", weight_name=["ip_adapter_plus_general.bin"])
def load_pose_pipeline():
global pipe_pose
controlnet_pose = ControlNetModel.from_pretrained(f"{ckpt_dir_pose}", revision=None).half().to(device)
pipe_pose = StableDiffusionXLControlNetImg2ImgPipeline(
vae=vae,
controlnet=controlnet_pose,
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_pose.load_ip_adapter(f'{ckpt_dir_ipa}', subfolder="", weight_name=["ip_adapter_plus_general.bin"])
def switch_to_canny():
clear_resources()
load_canny_pipeline()
return gr.update(visible=True)
def switch_to_depth():
clear_resources()
load_depth_pipeline()
return gr.update(visible=True)
def switch_to_pose():
clear_resources()
load_pose_pipeline()
return gr.update(visible=True)
def zip_images(gallery, zip_name):
if gallery is None or len(gallery) == 0:
return None
if not zip_name:
zip_name = "generated_images.zip"
with ZipFile(zip_name, "w") as zipObj:
for i, image in enumerate(gallery):
temp_file = f"temp_{i}.png"
Image.open(image[0]).save(temp_file)
#image.save(temp_file)
zipObj.write(temp_file, f"image_{i}.png")
os.remove(temp_file)
return zip_name
def update_zip_name(ipa_image_file):
#print(ipa_image_file)
if ipa_image_file is not None and type(ipa_image_file) == type(""):
name = ipa_image_file.split("/")[-1].split('.')[0]
return "{}_generated_images.zip".format(name)
return "generated_images.zip"
with gr.Blocks(css=css) as Kolors:
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")
ipa_image = gr.Image(type="pil", visible = False)
ipa_image_file = gr.Image(type = "filepath", label="IP-Adapter-Image")
with gr.Row():
num_images = gr.Slider(
label="Number of Images",
minimum=1,
maximum=10,
step=1,
value=1,
)
with gr.Accordion("Advanced Settings", open=False):
negative_prompt = gr.Textbox(
label="Negative prompt",
placeholder="Enter a negative prompt",
visible=True,
value="nsfw๏ผŒ่„ธ้ƒจ้˜ดๅฝฑ๏ผŒไฝŽๅˆ†่พจ็Ž‡๏ผŒ็ณŸ็ณ•็š„่งฃๅ‰–็ป“ๆž„ใ€็ณŸ็ณ•็š„ๆ‰‹๏ผŒ็ผบๅคฑๆ‰‹ๆŒ‡ใ€่ดจ้‡ๆœ€ๅทฎใ€ไฝŽ่ดจ้‡ใ€jpegไผชๅฝฑใ€ๆจก็ณŠใ€็ณŸ็ณ•๏ผŒ้ป‘่„ธ๏ผŒ้œ“่™น็ฏ"
)
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")
depth_button = gr.Button("Depth", elem_id="button")
pose_button = gr.Button("Pose", elem_id="button")
with gr.Column(elem_id="col-right"):
result = gr.Gallery(label="Result", show_label=False, columns=3)
seed_used = gr.Number(label="Seed Used")
zip_name = gr.Textbox(label="Zip File Name", value="generated_images.zip")
zip_button = gr.Button("Zip Images as Zip", elem_id="button")
download_file = gr.File(label="Download Zip File of Image")
with gr.Row():
gr.Examples(
fn=infer_canny,
examples=canny_examples,
inputs=[prompt, image, ipa_image_file, num_images],
outputs=[result, seed_used],
label="Canny"
)
with gr.Row():
gr.Examples(
fn=infer_depth,
examples=depth_examples,
inputs=[prompt, image, ipa_image_file, num_images],
outputs=[result, seed_used],
label="Depth"
)
with gr.Row():
gr.Examples(
fn=infer_pose,
examples=pose_examples,
inputs=[prompt, image, ipa_image_file, num_images],
outputs=[result, seed_used],
label="Pose"
)
canny_button.click(
fn=switch_to_canny,
outputs=[canny_button]
).then(
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, num_images],
outputs=[result, seed_used]
)
depth_button.click(
fn=switch_to_depth,
outputs=[depth_button]
).then(
fn=infer_depth,
inputs=[prompt, image, ipa_image, negative_prompt, seed, randomize_seed, guidance_scale, num_inference_steps, controlnet_conditioning_scale, control_guidance_end, strength, ip_scale, num_images],
outputs=[result, seed_used]
)
pose_button.click(
fn=switch_to_pose,
outputs=[pose_button]
).then(
fn=infer_pose,
inputs=[prompt, image, ipa_image, negative_prompt, seed, randomize_seed, guidance_scale, num_inference_steps, controlnet_conditioning_scale, control_guidance_end, strength, ip_scale, num_images],
outputs=[result, seed_used]
)
ipa_image_file.change(
fn = lambda x: Image.open(x),
inputs = [ipa_image_file],
outputs = [ipa_image]
)
ipa_image_file.change(
fn=update_zip_name,
inputs=[ipa_image_file],
outputs=[zip_name]
)
zip_button.click(
fn=zip_images,
inputs=[result, zip_name],
outputs=download_file
)
Kolors.queue().launch(debug=True, share=True)