cosxl / app.py
multimodalart's picture
Update app.py
13334d2 verified
import gradio as gr
from diffusers import StableDiffusionXLPipeline, EDMEulerScheduler, StableDiffusionXLInstructPix2PixPipeline, AutoencoderKL
from custom_pipeline import CosStableDiffusionXLInstructPix2PixPipeline
from huggingface_hub import hf_hub_download
import numpy as np
import math
import spaces
import torch
from PIL import Image
edit_file = hf_hub_download(repo_id="stabilityai/cosxl", filename="cosxl_edit.safetensors")
normal_file = hf_hub_download(repo_id="stabilityai/cosxl", filename="cosxl.safetensors")
def set_timesteps_patched(self, num_inference_steps: int, device = None):
self.num_inference_steps = num_inference_steps
ramp = np.linspace(0, 1, self.num_inference_steps)
sigmas = torch.linspace(math.log(self.config.sigma_min), math.log(self.config.sigma_max), len(ramp)).exp().flip(0)
sigmas = (sigmas).to(dtype=torch.float32, device=device)
self.timesteps = self.precondition_noise(sigmas)
self.sigmas = torch.cat([sigmas, torch.zeros(1, device=sigmas.device)])
self._step_index = None
self._begin_index = None
self.sigmas = self.sigmas.to("cpu") # to avoid too much CPU/GPU communication
def resize_image(image, resolution):
original_width, original_height = image.size
if original_width > original_height:
new_width = resolution
new_height = int((resolution / original_width) * original_height)
else:
new_height = resolution
new_width = int((resolution / original_height) * original_width)
resized_img = image.resize((new_width, new_height), Image.Resampling.LANCZOS)
return resized_img
EDMEulerScheduler.set_timesteps = set_timesteps_patched
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
pipe_edit = StableDiffusionXLInstructPix2PixPipeline.from_single_file(
edit_file, num_in_channels=8, is_cosxl_edit=True, vae=vae, torch_dtype=torch.float16,
)
pipe_edit.scheduler = EDMEulerScheduler(sigma_min=0.002, sigma_max=120.0, sigma_data=1.0, prediction_type="v_prediction")
pipe_edit.to("cuda")
pipe_normal = StableDiffusionXLPipeline.from_single_file(normal_file, torch_dtype=torch.float16, vae=vae)
pipe_normal.scheduler = EDMEulerScheduler(sigma_min=0.002, sigma_max=120.0, sigma_data=1.0, prediction_type="v_prediction")
pipe_normal.to("cuda")
@spaces.GPU
def run_normal(prompt, negative_prompt="", guidance_scale=7, steps=20, progress=gr.Progress(track_tqdm=True)):
return pipe_normal(prompt, negative_prompt=negative_prompt, guidance_scale=guidance_scale, num_inference_steps=steps).images[0]
@spaces.GPU
def run_edit(image, prompt, negative_prompt="", guidance_scale=7, steps=20, progress=gr.Progress(track_tqdm=True)):
image = resize_image(image, 1024)
print("Image resized to ", image.size)
width, height = image.size
#image.resize((resolution, resolution))
return pipe_edit(prompt=prompt,image=image,height=height,width=width,negative_prompt=negative_prompt, guidance_scale=guidance_scale,num_inference_steps=steps).images[0]
css = '''
.gradio-container{
max-width: 768px !important;
margin: 0 auto;
}
'''
normal_examples = ["portrait photo of a girl, photograph, highly detailed face, depth of field, moody light, golden hour, style by Dan Winters, Russell James, Steve McCurry, centered, extremely detailed, Nikon D850, award winning photography", "backlit photography of a dog", "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k", "A photo of beautiful mountain with realistic sunset and blue lake, highly detailed, masterpiece"]
edit_examples = [["mountain.png", "make it a cloudy day"], ["painting.png", "make the earring fancier"]]
with gr.Blocks(css=css) as demo:
gr.Markdown('''# CosXL demo
Unofficial demo for CosXL, a SDXL model tuned to produce full color range images. CosXL Edit allows you to perform edits on images. Both have a [non-commercial community license](https://huggingface.co/stabilityai/cosxl/blob/main/LICENSE)
''')
with gr.Tab("CosXL Edit"):
with gr.Group():
image_edit = gr.Image(label="Image you would like to edit", type="pil")
with gr.Row():
prompt_edit = gr.Textbox(show_label=False, scale=4, placeholder="Edit instructions, e.g.: Make the day cloudy")
button_edit = gr.Button("Generate", min_width=120)
output_edit = gr.Image(label="Your result image", interactive=False)
with gr.Accordion("Advanced Settings", open=False):
negative_prompt_edit = gr.Textbox(label="Negative Prompt")
guidance_scale_edit = gr.Number(label="Guidance Scale", value=7)
steps_edit = gr.Slider(label="Steps", minimum=10, maximum=50, value=20)
gr.Examples(examples=edit_examples, fn=run_edit, inputs=[image_edit, prompt_edit], outputs=[output_edit], cache_examples=True)
with gr.Tab("CosXL"):
with gr.Group():
with gr.Row():
prompt_normal = gr.Textbox(show_label=False, scale=4, placeholder="Your prompt, e.g.: backlit photography of a dog")
button_normal = gr.Button("Generate", min_width=120)
output_normal = gr.Image(label="Your result image", interactive=False)
with gr.Accordion("Advanced Settings", open=False):
negative_prompt_normal = gr.Textbox(label="Negative Prompt")
guidance_scale_normal = gr.Number(label="Guidance Scale", value=7)
steps_normal = gr.Slider(label="Steps", minimum=10, maximum=50, value=20)
gr.Examples(examples=normal_examples, fn=run_normal, inputs=[prompt_normal], outputs=[output_normal], cache_examples="lazy")
gr.on(
triggers=[
button_normal.click,
prompt_normal.submit
],
fn=run_normal,
inputs=[prompt_normal, negative_prompt_normal, guidance_scale_normal, steps_normal],
outputs=[output_normal],
)
gr.on(
triggers=[
button_edit.click,
prompt_edit.submit
],
fn=run_edit,
inputs=[image_edit, prompt_edit, negative_prompt_edit, guidance_scale_edit, steps_edit],
outputs=[output_edit]
)
if __name__ == "__main__":
demo.launch(share=True)