ciaochaos's picture
Update app.py
1e3e225
raw
history blame
3.97 kB
from PIL import Image
import gradio as gr
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, UniPCMultistepScheduler
import torch
torch.backends.cuda.matmul.allow_tf32 = True
controlnet = ControlNetModel.from_pretrained("ioclab/control_v1p_sd15_brightness", torch_dtype=torch.float16, use_safetensors=True)
pipe = StableDiffusionControlNetPipeline.from_pretrained(
"runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16,
)
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
pipe.enable_xformers_memory_efficient_attention()
pipe.enable_model_cpu_offload()
pipe.enable_attention_slicing()
def infer(prompt, negative_prompt, conditioning_image, num_inference_steps, size, guidance_scale, seed):
conditioning_image = Image.fromarray(conditioning_image)
conditioning_image = conditioning_image.convert('L')
g_cpu = torch.Generator()
if seed == -1:
generator = g_cpu.manual_seed(g_cpu.seed())
else:
generator = g_cpu.manual_seed(seed)
output_images = pipe(
prompt,
conditioning_image,
height=size,
width=size,
num_inference_steps=num_inference_steps,
generator=generator,
negative_prompt=negative_prompt,
guidance_scale=guidance_scale,
controlnet_conditioning_scale=1.0,
).images
return output_images
with gr.Blocks() as demo:
gr.Markdown(
"""
# ControlNet on Brightness
This is a demo on ControlNet based on brightness.
""")
with gr.Row():
with gr.Column():
prompt = gr.Textbox(
label="Prompt",
)
negative_prompt = gr.Textbox(
label="Negative Prompt",
)
conditioning_image = gr.Image(
label="Conditioning Image",
)
with gr.Accordion('Advanced options', open=False):
with gr.Row():
num_inference_steps = gr.Slider(
10, 40, 20,
step=1,
label="Steps",
)
size = gr.Slider(
256, 768, 512,
step=128,
label="Size",
)
with gr.Row():
guidance_scale = gr.Slider(
label='Guidance Scale',
minimum=0.1,
maximum=30.0,
value=7.0,
step=0.1
)
seed = gr.Slider(
label='Seed',
value=-1,
minimum=-1,
maximum=2147483647,
step=1,
# randomize=True
)
submit_btn = gr.Button(
value="Submit",
variant="primary"
)
with gr.Column(min_width=300):
output = gr.Gallery(
label="Result",
)
submit_btn.click(
fn=infer,
inputs=[
prompt, negative_prompt, conditioning_image, num_inference_steps, size, guidance_scale, seed
],
outputs=output
)
gr.Examples(
examples=[
["a village in the mountains", "monochrome", "./conditioning_images/conditioning_image_1.jpg"],
["three people walking in an alleyway with hats and pants", "monochrome", "./conditioning_images/conditioning_image_2.jpg"],
["an anime character, natural skin", "monochrome", "./conditioning_images/conditioning_image_3.jpg"],
["white object standing on colorful ground", "monochrome", "./conditioning_images/conditioning_image_4.jpg"],
],
inputs=[
prompt, negative_prompt, conditioning_image
],
)
demo.launch()