Spaces:
Paused
Paused
File size: 12,000 Bytes
2091d9d 5fc9884 2091d9d 31b607a 2091d9d d51b2d2 2091d9d d51b2d2 2091d9d 2bf41dd 2091d9d d51b2d2 2091d9d d51b2d2 2091d9d d51b2d2 f6debc2 2091d9d d51b2d2 2091d9d d51b2d2 2091d9d d51b2d2 2091d9d d51b2d2 2091d9d bc10e06 d51b2d2 46ea192 d51b2d2 bc10e06 617e96c 46ea192 2091d9d d51b2d2 2091d9d d51b2d2 2091d9d 5c041f6 2091d9d e7039e8 2091d9d d51b2d2 2091d9d d51b2d2 2091d9d d51b2d2 2091d9d a81339e 2091d9d d51b2d2 2091d9d d51b2d2 2091d9d d51b2d2 2091d9d d51b2d2 2091d9d 46ea192 2091d9d 46ea192 2091d9d d51b2d2 46ea192 2091d9d d51b2d2 2091d9d ef8a4ee 2091d9d 54511f0 2091d9d 094fe55 31b607a 6b7bef0 81c93cd 6b7bef0 d51b2d2 6b7bef0 d51b2d2 6b7bef0 d51b2d2 46ea192 d51b2d2 46ea192 d51b2d2 2091d9d d51b2d2 46ea192 d51b2d2 46ea192 d51b2d2 46ea192 d51b2d2 46ea192 d51b2d2 46ea192 d51b2d2 46ea192 d51b2d2 46ea192 d51b2d2 2091d9d 46ea192 2091d9d 46ea192 2091d9d 10356b1 094fe55 10356b1 094fe55 10356b1 2091d9d d51b2d2 2091d9d d51b2d2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 |
import cv2
import torch
import random
import tempfile
import numpy as np
from pathlib import Path
from PIL import Image
from diffusers import (
ControlNetModel,
StableDiffusionXLControlNetPipeline,
UNet2DConditionModel,
EulerDiscreteScheduler,
)
import spaces
import gradio as gr
from huggingface_hub import hf_hub_download, snapshot_download
from ip_adapter import IPAdapterXL
from safetensors.torch import load_file
from rembg import remove
snapshot_download(
repo_id="h94/IP-Adapter", allow_patterns="sdxl_models/*", local_dir="."
)
# global variable
MAX_SEED = np.iinfo(np.int32).max
device = "cuda" if torch.cuda.is_available() else "cpu"
dtype = torch.float16 if str(device).__contains__("cuda") else torch.float32
# initialization
base_model_path = "stabilityai/stable-diffusion-xl-base-1.0"
image_encoder_path = "sdxl_models/image_encoder"
ip_ckpt = "sdxl_models/ip-adapter_sdxl.bin"
controlnet_path = "diffusers/controlnet-canny-sdxl-1.0"
controlnet = ControlNetModel.from_pretrained(
controlnet_path, use_safetensors=False, torch_dtype=torch.float16
).to(device)
# load SDXL lightnining
pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
base_model_path,
controlnet=controlnet,
torch_dtype=torch.float16,
variant="fp16",
add_watermarker=False,
).to(device)
pipe.set_progress_bar_config(disable=True)
pipe.scheduler = EulerDiscreteScheduler.from_config(
pipe.scheduler.config, timestep_spacing="trailing", prediction_type="epsilon"
)
pipe.unet.load_state_dict(
load_file(
hf_hub_download(
"ByteDance/SDXL-Lightning", "sdxl_lightning_2step_unet.safetensors"
),
device="cuda",
)
)
# load ip-adapter
# target_blocks=["block"] for original IP-Adapter
# target_blocks=["up_blocks.0.attentions.1"] for style blocks only
# target_blocks = ["up_blocks.0.attentions.1", "down_blocks.2.attentions.1"] # for style+layout blocks
ip_model = IPAdapterXL(
pipe,
image_encoder_path,
ip_ckpt,
device,
target_blocks=["up_blocks.0.attentions.1"],
)
def resize_img(
input_image,
max_side=1280,
min_side=1024,
size=None,
pad_to_max_side=False,
mode=Image.BILINEAR,
base_pixel_number=64,
):
w, h = input_image.size
if size is not None:
w_resize_new, h_resize_new = size
else:
ratio = min_side / min(h, w)
w, h = round(ratio * w), round(ratio * h)
ratio = max_side / max(h, w)
input_image = input_image.resize([round(ratio * w), round(ratio * h)], mode)
w_resize_new = (round(ratio * w) // base_pixel_number) * base_pixel_number
h_resize_new = (round(ratio * h) // base_pixel_number) * base_pixel_number
input_image = input_image.resize([w_resize_new, h_resize_new], mode)
if pad_to_max_side:
res = np.ones([max_side, max_side, 3], dtype=np.uint8) * 255
offset_x = (max_side - w_resize_new) // 2
offset_y = (max_side - h_resize_new) // 2
res[offset_y : offset_y + h_resize_new, offset_x : offset_x + w_resize_new] = (
np.array(input_image)
)
input_image = Image.fromarray(res)
return input_image
examples = [
[
"./asset/0.jpg",
None,
"3D model, cute monster, high quality",
1.0,
0.0,
],
[
"./asset/2.jpg",
"./asset/house.jpg",
"3d model, house, kawai, cute, sci-fi, solarpunk, high quality",
1.0,
0.6,
],
]
def run_for_examples(style_image, source_image, prompt, scale, control_scale):
return create_image(
image_pil=style_image,
input_image=source_image,
prompt=prompt,
n_prompt="text, watermark, lowres, low quality, worst quality, deformed, glitch, low contrast, noisy, saturation, blurry",
scale=scale,
control_scale=control_scale,
guidance_scale=0.0,
num_inference_steps=2,
seed=42,
target="Load only style blocks",
neg_content_prompt="",
neg_content_scale=0,
)
@spaces.GPU
def create_image(
image_pil,
input_image,
prompt,
n_prompt,
scale,
control_scale,
guidance_scale,
num_inference_steps,
seed,
target="Load only style blocks",
neg_content_prompt=None,
neg_content_scale=0,
):
seed = random.randint(0, MAX_SEED) if seed == -1 else seed
if target == "Load original IP-Adapter":
# target_blocks=["blocks"] for original IP-Adapter
ip_model = IPAdapterXL(
pipe, image_encoder_path, ip_ckpt, device, target_blocks=["blocks"]
)
elif target == "Load only style blocks":
# target_blocks=["up_blocks.0.attentions.1"] for style blocks only
ip_model = IPAdapterXL(
pipe,
image_encoder_path,
ip_ckpt,
device,
target_blocks=["up_blocks.0.attentions.1"],
)
elif target == "Load style+layout block":
# target_blocks = ["up_blocks.0.attentions.1", "down_blocks.2.attentions.1"] # for style+layout blocks
ip_model = IPAdapterXL(
pipe,
image_encoder_path,
ip_ckpt,
device,
target_blocks=["up_blocks.0.attentions.1", "down_blocks.2.attentions.1"],
)
if input_image is not None:
input_image = resize_img(input_image, max_side=1024)
cv_input_image = pil_to_cv2(input_image)
detected_map = cv2.Canny(cv_input_image, 50, 200)
canny_map = Image.fromarray(cv2.cvtColor(detected_map, cv2.COLOR_BGR2RGB))
else:
canny_map = Image.new("RGB", (1024, 1024), color=(255, 255, 255))
control_scale = 0
if float(control_scale) == 0:
canny_map = canny_map.resize((1024, 1024))
if len(neg_content_prompt) > 0 and neg_content_scale != 0:
images = ip_model.generate(
pil_image=image_pil,
prompt=prompt,
negative_prompt=n_prompt,
scale=scale,
guidance_scale=guidance_scale,
num_samples=1,
num_inference_steps=num_inference_steps,
seed=seed,
image=canny_map,
controlnet_conditioning_scale=float(control_scale),
neg_content_prompt=neg_content_prompt,
neg_content_scale=neg_content_scale,
)
else:
images = ip_model.generate(
pil_image=image_pil,
prompt=prompt,
negative_prompt=n_prompt,
scale=scale,
guidance_scale=guidance_scale,
num_samples=1,
num_inference_steps=num_inference_steps,
seed=seed,
image=canny_map,
controlnet_conditioning_scale=float(control_scale),
)
image = images[0]
with tempfile.NamedTemporaryFile(suffix=".jpg", delete=False) as tmpfile:
image.save(tmpfile, "JPEG", quality=80, optimize=True, progressive=True)
return Path(tmpfile.name)
def pil_to_cv2(image_pil):
image_np = np.array(image_pil)
image_cv2 = cv2.cvtColor(image_np, cv2.COLOR_RGB2BGR)
return image_cv2
# Description
title = r"""
<h1 align="center">I2I mit SDXL-Lightning & IP-Adapter</h1>
"""
description = r"""
<b>ARM <3 GoldExtra Testversion<br>
<b>Wir schauen uns gut funktionierende Prompts. Bitte diese notieren und an Hidéo weiterleiten!</b><br>
"""
article = r"""
<br>
Bei Fragen: <a href="mailto:hideo@artificialmuseum.com">Mail an Hidéo</a>
"""
block = gr.Blocks()
with block:
# description
gr.Markdown(title)
gr.Markdown(description)
with gr.Tabs():
with gr.Row():
with gr.Column():
with gr.Row():
with gr.Column():
with gr.Row():
# with gr.Column():
image_pil_pil = gr.Image(label="Style Image", type="pil")
with gr.Column():
prompt = gr.Textbox(
label="Prompt",
value="3d render, 3d model, clean 3d style, cute space monster, white backround, cinematic lighting,",
)
scale = gr.Slider(
minimum=0, maximum=2.0, step=0.01, value=1.0, label="Scale"
)
with gr.Accordion(open=False, label="Details (optional)"):
target = gr.Radio(
[
"Load only style blocks",
"Load style+layout block",
"Load original IP-Adapter",
],
value="Load only style blocks",
label="Style mode (optional, sb works best!)",
)
with gr.Column():
src_image_pil = gr.Image(
label="Source Image (optional)", type="pil"
)
control_scale = gr.Slider(
minimum=0,
maximum=1.0,
step=0.01,
value=0.5,
label="ControlNet Scale (test this!)",
)
n_prompt = gr.Textbox(
label="Negative Prompt // n_prompt",
value="text, watermark, lowres, low quality, worst quality, deformed, glitch, low contrast, noisy, saturation, blurry",
)
neg_content_prompt = gr.Textbox(
label="Negative Content Prompt (Ignore this!)", value=""
)
neg_content_scale = gr.Slider(
minimum=0,
maximum=1.0,
step=0.01,
value=0.5,
label="NCS (Ignore this!) // neg_content_scale",
)
guidance_scale = gr.Slider(
minimum=0,
maximum=10.0,
step=0.01,
value=0.0,
label="Guidance Scale (test this!)",
)
num_inference_steps = gr.Slider(
minimum=2,
maximum=50.0,
step=1.0,
value=2,
label="Inference Steps (optional but test with 2+)",
)
seed = gr.Slider(
minimum=-1,
maximum=MAX_SEED,
value=-1,
step=1,
label="Seed Value (Seed-Proof) // -1 == random",
)
generate_button = gr.Button("Simsalabim")
with gr.Column():
generated_image = gr.Image(label="Magix uWu")
inputs = [
image_pil,
src_image_pil,
prompt,
n_prompt,
scale,
control_scale,
guidance_scale,
num_inference_steps,
seed,
target,
neg_content_prompt,
neg_content_scale,
]
outputs = [generated_image]
gr.on(
triggers=[
# prompt.input,
generate_button.click,
# guidance_scale.input,
# scale.input,
# control_scale.input,
# seed.input,
],
fn=create_image,
inputs=inputs,
outputs=outputs,
show_progress="minimal",
show_api=False,
trigger_mode="always_last",
)
gr.Examples(
examples=examples,
inputs=[image_pil, src_image_pil, prompt, scale, control_scale],
fn=run_for_examples,
outputs=[generated_image],
cache_examples=True,
)
gr.Markdown(article)
block.queue(api_open=False)
block.launch(show_api=False) |