multimodalart's picture
Create app.py
701027b verified
raw
history blame
4.38 kB
import gradio as gr
import numpy as np
import random
import torch
from diffusers import StableDiffusion3Pipeline, SD3Transformer2DModel, FlowMatchEulerDiscreteScheduler
device = "cuda" if torch.cuda.is_available() else "cpu"
dtype = torch.float16
repo = "diffusers-internal-dev/private-model"
transformer_repo= "diffusers-internal-dev/pm-revamp"
transformer = SD3Transformer2DModel.from_pretrained(transformer_repo, subfolder="transformer", torch_dtype=dtype)
pipe = StableDiffusion3Pipeline.from_pretrained(repo, transformer=transformer, torch_dtype=torch.float16).to(device)
pipe.scheduler = FlowMatchEulerDiscreteScheduler.from_config(pipe.scheduler.config, shift=3.0)
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1344
def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, progress=gr.Progress(track_tqdm=True)):
if randomize_seed:
seed = random.randint(0, MAX_SEED)
generator = torch.Generator().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
).images[0]
return image, seed
examples = [
"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
"An astronaut riding a green horse",
"A delicious ceviche cheesecake slice",
]
css="""
#col-container {
margin: 0 auto;
max-width: 520px;
}
"""
with gr.Blocks(css=css) as demo:
with gr.Column(elem_id="col-container"):
gr.Markdown(f"""
# Stable Diffusion 3 Medium demo
Demo of [Stable Diffusion 3 Medium](#) - try out [Stable Assistant](https://stability.ai/stable-assistant) for chatting, [Stable Artisan](https://stability.ai/stable-artisan) for a discord bot, our API or run locally with [ComfyUI](#) or [diffusers](#)
""")
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)
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=256,
maximum=MAX_IMAGE_SIZE,
step=64,
value=1024,
)
height = gr.Slider(
label="Height",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=64,
value=1024,
)
with gr.Row():
guidance_scale = gr.Slider(
label="Guidance scale",
minimum=0.0,
maximum=10.0,
step=0.1,
value=4.0,
)
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=50,
step=1,
value=28,
)
gr.Examples(
examples = examples,
inputs = [prompt]
)
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]
)