Spaces:
Running
on
Zero
Running
on
Zero
File size: 4,566 Bytes
5d54e97 d3c4eaa 5d54e97 d3c4eaa 6e4f503 5d54e97 20bec0f 5d54e97 d3c4eaa 5d54e97 d3c4eaa 5d54e97 d3c4eaa 5d54e97 d3c4eaa 5d54e97 d3c4eaa 5d54e97 d3c4eaa 5d54e97 d3c4eaa 5d54e97 6e4f503 5d54e97 d3c4eaa 5d54e97 |
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 |
import gradio as gr
import numpy as np
import random
import spaces
from diffusers import ChromaPipeline
import torch
device = "cuda" if torch.cuda.is_available() else "cpu"
model_repo_id = "lodestones/Chroma1-HD"
if torch.cuda.is_available():
torch_dtype = torch.bfloat16
else:
torch_dtype = torch.float32
pipe = ChromaPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
pipe = pipe.to(device)
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024
@spaces.GPU()
def infer(prompt, negative_prompt="low quality, ugly, unfinished, out of focus, deformed, disfigure, blurry, smudged, restricted palette, flat colors", seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=3.0, num_inference_steps=40, progress=gr.Progress(track_tqdm=True)):
if randomize_seed:
seed = random.randint(0, MAX_SEED)
generator = torch.Generator(device).manual_seed(seed)
image = pipe(
prompt=prompt,
negative_prompt=negative_prompt,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
width=width,
height=height,
generator=generator,
num_images_per_prompt=1
).images[0]
return image, seed
examples = [
"A high-fashion close-up portrait of a blonde woman in clear sunglasses. The image uses a bold teal and red color split for dramatic lighting. The background is a simple teal-green. The photo is sharp and well-composed, and is designed for viewing with anaglyph 3D glasses for optimal effect. It looks professionally done.",
"A dog eating pizza",
"The spirit of a tamagotchi wandering in San Francisco",
]
css="""
#col-container {
margin: 0 auto;
max-width: 760px;
}
#button{
align-self: stretch;
}
"""
with gr.Blocks(css=css) as demo:
with gr.Column(elem_id="col-container"):
gr.Markdown(f"""
# Chroma1-HD
[Chroma1-HD](https://huggingface.co/lodestones/Chroma1-HD) is an 8.9B parameter text-to-image foundational model based on FLUX.1-schnell
""")
with gr.Row():
prompt = gr.Text(
label="Prompt",
max_lines=1,
placeholder="Enter your prompt",
)
negative_prompt = gr.Text(
label="Negative prompt",
max_lines=1,
placeholder="Enter a negative prompt",
value="low quality, ugly, unfinished, out of focus, deformed, disfigure, blurry, smudged, restricted palette, flat colors"
)
with gr.Row():
run_button = gr.Button("Run", scale=1, elem_id="button")
result = gr.Image(label="Result", show_label=False)
with gr.Accordion("Advanced Settings", open=False):
guidance_scale = gr.Slider(
label="Guidance Scale",
minimum=1.0,
maximum=10.0,
step=0.1,
value=3.0,
)
seed = gr.Slider(
label="Seed",
minimum=0,
maximum=MAX_SEED,
step=1,
value=433,
)
randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
with gr.Row():
width = gr.Slider(
label="Width",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=32,
value=1024,
)
height = gr.Slider(
label="Height",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=32,
value=1024,
)
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=100,
step=1,
value=40,
)
gr.Examples(
examples=examples,
inputs=[prompt],
outputs=[result, seed],
fn=infer,
cache_examples="lazy"
)
gr.on(
triggers=[run_button.click, prompt.submit, negative_prompt.submit],
fn=infer,
inputs=[prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
outputs=[result, seed]
)
demo.queue().launch() |