multimodalart's picture
Update app.py
ec58781 verified
raw
history blame
3.82 kB
import gradio as gr
import numpy as np
import spaces
import torch
import spaces
import random
from diffusers import FluxControlPipeline, FluxTransformer2DModel
from controlnet_aux import CannyDetector
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 2048
pipe = FluxControlPipeline.from_pretrained("black-forest-labs/FLUX.1-Canny-dev", torch_dtype=torch.bfloat16).to("cuda")
processor = CannyDetector()
@spaces.GPU
def infer(control_image, prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=3.5, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)):
if randomize_seed:
seed = random.randint(0, MAX_SEED)
control_image = processor(control_image, low_threshold=50, high_threshold=200, detect_resolution=1024, image_resolution=1024)
image = pipe(
prompt=prompt,
control_image=control_image,
height=height,
width=width,
num_inference_steps=num_inference_steps,
guidance_scale=guidance_scale,
generator=torch.Generator().manual_seed(seed),
).images[0]
return image, seed
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"""# FLUX.1 Canny [dev]
12B param rectified flow transformer structural conditioning tuned, guidance-distilled from [FLUX.1 [pro]](https://blackforestlabs.ai/)
[[non-commercial license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md)] [[blog](https://blackforestlabs.ai/announcing-black-forest-labs/)] [[model](https://huggingface.co/black-forest-labs/FLUX.1-dev)]
""")
control_image = gr.Image(label="Upload the image for control", type="pil")
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):
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=32,
value=1024,
)
height = gr.Slider(
label="Height",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=32,
value=1024,
)
with gr.Row():
guidance_scale = gr.Slider(
label="Guidance Scale",
minimum=1,
maximum=15,
step=0.1,
value=3.5,
)
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=50,
step=1,
value=28,
)
gr.on(
triggers=[run_button.click, prompt.submit],
fn = infer,
inputs = [control_image, prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
outputs = [result, seed]
)
demo.launch()