Spaces:
Sleeping
Sleeping
File size: 9,993 Bytes
50ef0b7 73dd322 9333076 50ef0b7 d5745cb 50ef0b7 5280b61 50ef0b7 5280b61 d5745cb 5280b61 50ef0b7 716ff7f daa1993 5280b61 11dcdf1 3c4a949 ff1979b 5280b61 50ef0b7 d317594 50ef0b7 5280b61 d5745cb 50ef0b7 d5745cb 50ef0b7 5e73db7 50ef0b7 c606e76 5280b61 c606e76 5280b61 c606e76 5280b61 c606e76 5280b61 c606e76 5280b61 c606e76 5280b61 c606e76 5e73db7 c606e76 5280b61 194fd97 5280b61 54ecd01 194fd97 5280b61 194fd97 5280b61 194fd97 50ef0b7 5280b61 5e73db7 d5745cb 50ef0b7 |
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 |
import gradio as gr
import numpy as np
import random
import os
import torch
from diffusers import StableDiffusionPipeline, ControlNetModel, StableDiffusionControlNetPipeline
from diffusers.utils import load_image
from peft import PeftModel, LoraConfig
from rembg import remove
device = "cuda" if torch.cuda.is_available() else "cpu"
model_id_default = "stable-diffusion-v1-5/stable-diffusion-v1-5"
if torch.cuda.is_available():
torch_dtype = torch.float16
else:
torch_dtype = torch.float32
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024
# @spaces.GPU #[uncomment to use ZeroGPU]
def infer(
prompt,
negative_prompt,
width=512,
height=512,
model_id=model_id_default,
seed=42,
guidance_scale=7.0,
lora_scale=1.0,
num_inference_steps=20,
controlnet_checkbox=False,
controlnet_strength=0.0,
controlnet_mode="edge_detection",
controlnet_image=None,
ip_adapter_checkbox=False,
ip_adapter_scale=0.0,
ip_adapter_image=None,
del_background=False,
progress=gr.Progress(track_tqdm=True),
):
ckpt_dir='./model_output'
unet_sub_dir = os.path.join(ckpt_dir, "unet")
text_encoder_sub_dir = os.path.join(ckpt_dir, "text_encoder")
if model_id is None:
raise ValueError("Please specify the base model name or path")
generator = torch.Generator(device).manual_seed(seed)
params = {'prompt': prompt,
'negative_prompt': negative_prompt,
'guidance_scale': guidance_scale,
'num_inference_steps': num_inference_steps,
'width': width,
'height': height,
'generator': generator
}
if controlnet_checkbox:
if controlnet_mode == "depth_map":
controlnet = ControlNetModel.from_pretrained(
"lllyasviel/sd-controlnet-depth",
cache_dir="./models_cache",
torch_dtype=torch_dtype
)
elif controlnet_mode == "pose_estimation":
controlnet = ControlNetModel.from_pretrained(
"lllyasviel/sd-controlnet-openpose",
cache_dir="./models_cache",
torch_dtype=torch_dtype
)
elif controlnet_mode == "normal_map":
controlnet = ControlNetModel.from_pretrained(
"lllyasviel/sd-controlnet-normal",
cache_dir="./models_cache",
torch_dtype=torch_dtype
)
elif controlnet_mode == "scribbles":
controlnet = ControlNetModel.from_pretrained(
"lllyasviel/sd-controlnet-scribble",
cache_dir="./models_cache",
torch_dtype=torch_dtype
)
else:
controlnet = ControlNetModel.from_pretrained(
"lllyasviel/sd-controlnet-canny",
cache_dir="./models_cache",
torch_dtype=torch_dtype
)
pipe = StableDiffusionControlNetPipeline.from_pretrained(model_id,
controlnet=controlnet,
torch_dtype=torch_dtype,
safety_checker=None).to(device)
params['image'] = controlnet_image
params['controlnet_conditioning_scale'] = float(controlnet_strength)
else:
pipe = StableDiffusionPipeline.from_pretrained(model_id,
torch_dtype=torch_dtype,
safety_checker=None).to(device)
pipe.unet = PeftModel.from_pretrained(pipe.unet, unet_sub_dir)
pipe.text_encoder = PeftModel.from_pretrained(pipe.text_encoder, text_encoder_sub_dir)
pipe.unet.load_state_dict({k: lora_scale*v for k, v in pipe.unet.state_dict().items()})
pipe.text_encoder.load_state_dict({k: lora_scale*v for k, v in pipe.text_encoder.state_dict().items()})
if torch_dtype in (torch.float16, torch.bfloat16):
pipe.unet.half()
pipe.text_encoder.half()
if ip_adapter_checkbox:
pipe.load_ip_adapter("h94/IP-Adapter", subfolder="models", weight_name="ip-adapter-plus_sd15.bin")
pipe.set_ip_adapter_scale(ip_adapter_scale)
params['ip_adapter_image'] = ip_adapter_image
pipe.to(device)
if del_background:
return remove(pipe(**params).images[0])
else:
return pipe(**params).images[0]
css = """
#col-container {
margin: 0 auto;
max-width: 640px;
}
"""
def controlnet_params(show_extra):
return gr.update(visible=show_extra)
with gr.Blocks(css=css, fill_height=True) as demo:
with gr.Column(elem_id="col-container"):
gr.Markdown(" # Text-to-Image demo")
with gr.Row():
model_id = gr.Textbox(
label="Model ID",
max_lines=1,
placeholder="Enter model id",
value=model_id_default,
)
prompt = gr.Textbox(
label="Prompt",
max_lines=1,
placeholder="Enter your prompt",
)
negative_prompt = gr.Textbox(
label="Negative prompt",
max_lines=1,
placeholder="Enter your negative prompt",
)
with gr.Row():
seed = gr.Number(
label="Seed",
minimum=0,
maximum=MAX_SEED,
step=1,
value=42,
)
guidance_scale = gr.Slider(
label="Guidance scale",
minimum=0.0,
maximum=30.0,
step=0.1,
value=7.0, # Replace with defaults that work for your model
)
with gr.Row():
lora_scale = gr.Slider(
label="LoRA scale",
minimum=0.0,
maximum=1.0,
step=0.01,
value=1.0,
)
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=100,
step=1,
value=20, # Replace with defaults that work for your model
)
with gr.Row():
del_background = gr.Checkbox(
label="Delete background?",
value=False
)
with gr.Row():
controlnet_checkbox = gr.Checkbox(
label="ControlNet",
value=False
)
with gr.Column(visible=False) as controlnet_params:
controlnet_strength = gr.Slider(
label="ControlNet conditioning scale",
minimum=0.0,
maximum=1.0,
step=0.01,
value=1.0,
)
controlnet_mode = gr.Dropdown(
label="ControlNet mode",
choices=["edge_detection",
"depth_map",
"pose_estimation",
"normal_map",
"scribbles"],
value="edge_detection",
max_choices=1
)
controlnet_image = gr.Image(
label="ControlNet condition image",
type="pil",
format="png"
)
controlnet_checkbox.change(
fn=lambda x: gr.Row.update(visible=x),
inputs=controlnet_checkbox,
outputs=controlnet_params
)
with gr.Row():
ip_adapter_checkbox = gr.Checkbox(
label="IPAdapter",
value=False
)
with gr.Column(visible=False) as ip_adapter_params:
ip_adapter_scale = gr.Slider(
label="IPAdapter scale",
minimum=0.0,
maximum=1.0,
step=0.01,
value=1.0,
)
ip_adapter_image = gr.Image(
label="IPAdapter condition image",
type="pil"
)
ip_adapter_checkbox.change(
fn=lambda x: gr.Row.update(visible=x),
inputs=ip_adapter_checkbox,
outputs=ip_adapter_params
)
with gr.Accordion("Optional Settings", open=False):
with gr.Row():
width = gr.Slider(
label="Width",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=32,
value=512, # Replace with defaults that work for your model
)
height = gr.Slider(
label="Height",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=32,
value=512, # Replace with defaults that work for your model
)
run_button = gr.Button("Run", scale=0, variant="primary")
result = gr.Image(label="Result", show_label=False)
gr.on(
triggers=[run_button.click],
fn=infer,
inputs=[
prompt,
negative_prompt,
width,
height,
model_id,
seed,
guidance_scale,
lora_scale,
num_inference_steps,
controlnet_checkbox,
controlnet_strength,
controlnet_mode,
controlnet_image,
ip_adapter_checkbox,
ip_adapter_scale,
ip_adapter_image,
del_background,
],
outputs=[result],
)
if __name__ == "__main__":
demo.launch() |