Spaces:
Runtime error
Runtime error
File size: 6,515 Bytes
7359e88 ed2c8a0 7359e88 ed2c8a0 7359e88 1e0e726 7359e88 ed2c8a0 7359e88 ed2c8a0 7359e88 |
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 |
import gradio as gr
import numpy as np
import random
from PIL import Image
import os
import spaces
from diffusers import DiffusionPipeline, FlowMatchEulerDiscreteScheduler, StableDiffusionImg2ImgPipeline
import torch
from huggingface_hub import login
# Get token from Hugging Face Spaces secrets
# This will use the environment variable HF_ACCESS_TOKEN which is the standard in HF Spaces
hf_token = os.environ.get("HF_ACCESS_TOKEN")
if hf_token:
login(hf_token)
else:
print("Warning: HF_ACCESS_TOKEN not found in environment. Authentication may fail.")
device = "cuda" if torch.cuda.is_available() else "cpu"
model_repo_id = "stabilityai/stable-diffusion-3.5-medium"
if torch.cuda.is_available():
torch_dtype = torch.float16
else:
torch_dtype = torch.float32
# For text-to-image
pipe = DiffusionPipeline.from_pretrained(
model_repo_id,
torch_dtype=torch_dtype,
use_auth_token=True # This will use the token from login()
)
pipe.scheduler = FlowMatchEulerDiscreteScheduler.from_pretrained(
model_repo_id,
subfolder="scheduler",
shift=5,
use_auth_token=True
)
pipe = pipe.to(device)
# For image-to-image
img2img_pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
model_repo_id,
torch_dtype=torch_dtype,
use_auth_token=True
)
img2img_pipe.scheduler = FlowMatchEulerDiscreteScheduler.from_pretrained(
model_repo_id,
subfolder="scheduler",
shift=5,
use_auth_token=True
)
img2img_pipe = img2img_pipe.to(device)
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024
@spaces.GPU(duration=65)
def infer(
prompt,
negative_prompt="",
seed=42,
randomize_seed=False,
width=1024,
height=1024,
guidance_scale=1.5,
num_inference_steps=8,
input_image=None,
strength=0.8,
progress=gr.Progress(track_tqdm=True),
):
if randomize_seed:
seed = random.randint(0, MAX_SEED)
generator = torch.Generator().manual_seed(seed)
# Text-to-image if no input image is provided
if input_image is None:
image = pipe(
prompt=prompt,
negative_prompt=negative_prompt,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
width=width,
height=height,
generator=generator,
).images[0]
# Image-to-image if an input image is provided
else:
# Convert to PIL Image if it's a numpy array
if isinstance(input_image, np.ndarray):
input_image = Image.fromarray(input_image)
# Resize image to match requested dimensions
input_image = input_image.resize((width, height), Image.LANCZOS)
image = img2img_pipe(
prompt=prompt,
negative_prompt=negative_prompt,
image=input_image,
strength=strength,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
generator=generator,
).images[0]
return image, seed
examples = [
"A capybara wearing a suit holding a sign that reads Hello World",
]
css = """
#col-container {
margin: 0 auto;
max-width: 640px;
}
"""
with gr.Blocks(css=css) as demo:
with gr.Column(elem_id="col-container"):
gr.Markdown(" # TensorArt Stable Diffusion 3.5 Large TurboX")
gr.Markdown(
"[8-step distilled turbo model](https://huggingface.co/tensorart/stable-diffusion-3.5-large-TurboX)")
with gr.Row():
prompt = gr.Text(
label="Prompt",
show_label=False,
max_lines=1,
placeholder="Enter your prompt",
container=False,
)
run_button = gr.Button("Run", scale=0, variant="primary")
# Add image upload component
input_image = gr.Image(
label="Input Image (Optional)",
type="pil",
sources=["upload", "clipboard"],
)
result = gr.Image(label="Result", show_label=False)
with gr.Accordion("Advanced Settings", open=False):
negative_prompt = gr.Text(
label="Negative prompt",
max_lines=1,
placeholder="Enter a negative prompt",
)
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():
width = gr.Slider(
label="Width",
minimum=512,
maximum=MAX_IMAGE_SIZE,
step=32,
value=1024,
)
height = gr.Slider(
label="Height",
minimum=512,
maximum=MAX_IMAGE_SIZE,
step=32,
value=1024,
)
with gr.Row():
guidance_scale = gr.Slider(
label="Guidance scale",
minimum=0.0,
maximum=7.5,
step=0.1,
value=1.5,
)
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=50,
step=1,
value=8,
)
# Add strength parameter for image-to-image
strength = gr.Slider(
label="Strength (for image-to-image)",
minimum=0.0,
maximum=1.0,
step=0.01,
value=0.8,
info="How much to transform the reference image. 1.0 means complete transformation."
)
gr.Examples(examples=examples, inputs=[prompt], outputs=[result, seed], fn=infer, cache_examples=True,
cache_mode="lazy")
gr.on(
triggers=[run_button.click, prompt.submit],
fn=infer,
inputs=[
prompt,
negative_prompt,
seed,
randomize_seed,
width,
height,
guidance_scale,
num_inference_steps,
input_image,
strength,
],
outputs=[result, seed],
)
if __name__ == "__main__":
demo.launch() |