|
|
|
|
|
import random |
|
|
|
import gradio as gr |
|
import numpy as np |
|
import PIL.Image |
|
import torch |
|
import torchvision.transforms.functional as TF |
|
from diffusers import EulerAncestralDiscreteScheduler, StableDiffusionXLAdapterPipeline, T2IAdapter, AutoencoderKL |
|
|
|
DESCRIPTION = "# T2I-Adapter-SDXL Sketch" |
|
|
|
if not torch.cuda.is_available(): |
|
DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>" |
|
|
|
styles = [ |
|
{ |
|
"name": "Cinematic", |
|
"prompt": "cinematic still {prompt} . emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy", |
|
"negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured" |
|
}, |
|
{ |
|
"name": "3D Model", |
|
"prompt": "professional 3d model {prompt} . octane render, highly detailed, volumetric, dramatic lighting", |
|
"negative_prompt": "ugly, deformed, noisy, low poly, blurry, painting" |
|
}, |
|
{ |
|
"name": "Anime", |
|
"prompt": "anime artwork {prompt} . anime style, key visual, vibrant, studio anime, highly detailed", |
|
"negative_prompt": "photo, deformed, black and white, realism, disfigured, low contrast" |
|
}, |
|
{ |
|
"name": "Digital Art", |
|
"prompt": "concept art {prompt} . digital artwork, illustrative, painterly, matte painting, highly detailed", |
|
"negative_prompt": "photo, photorealistic, realism, ugly" |
|
}, |
|
{ |
|
"name": "Photographic", |
|
"prompt": "cinematic photo {prompt} . 35mm photograph, film, bokeh, professional, 4k, highly detailed", |
|
"negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly" |
|
}, |
|
{ |
|
"name": "Pixel art", |
|
"prompt": "pixel-art {prompt} . low-res, blocky, pixel art style, 8-bit graphics", |
|
"negative_prompt": "sloppy, messy, blurry, noisy, highly detailed, ultra textured, photo, realistic" |
|
}, |
|
{ |
|
"name": "Fantasy art", |
|
"prompt": "ethereal fantasy concept art of {prompt} . magnificent, celestial, ethereal, painterly, epic, majestic, magical, fantasy art, cover art, dreamy", |
|
"negative_prompt": "photographic, realistic, realism, 35mm film, dslr, cropped, frame, text, deformed, glitch, noise, noisy, off-center, deformed, cross-eyed, closed eyes, bad anatomy, ugly, disfigured, sloppy, duplicate, mutated, black and white" |
|
}, |
|
] |
|
|
|
styles = {k['name']: (k['prompt'], k['negative_prompt']) for k in styles} |
|
default_style = styles['Photographic'] |
|
style_names = list(styles.keys()) |
|
|
|
|
|
def apply_style(style, positive, negative=""): |
|
p, n = styles.get(style, default_style) |
|
return p.replace('{prompt}', positive), n + negative |
|
|
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu") |
|
if torch.cuda.is_available(): |
|
model_id = "stabilityai/stable-diffusion-xl-base-1.0" |
|
adapter = T2IAdapter.from_pretrained("TencentARC/t2i-adapter-sketch-sdxl-1.0", torch_dtype=torch.float16, variant="fp16") |
|
scheduler = EulerAncestralDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler") |
|
pipe = StableDiffusionXLAdapterPipeline.from_pretrained( |
|
model_id, |
|
vae=AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16), |
|
adapter=adapter, |
|
scheduler=scheduler, |
|
torch_dtype=torch.float16, |
|
variant="fp16", |
|
) |
|
pipe.to(device) |
|
else: |
|
pipe = None |
|
|
|
MAX_SEED = np.iinfo(np.int32).max |
|
|
|
|
|
def randomize_seed_fn(seed: int, randomize_seed: bool) -> int: |
|
if randomize_seed: |
|
seed = random.randint(0, MAX_SEED) |
|
return seed |
|
|
|
|
|
def run( |
|
image: PIL.Image.Image, |
|
prompt: str, |
|
negative_prompt: str, |
|
style=default_style, |
|
num_steps=25, |
|
guidance_scale=5, |
|
adapter_conditioning_scale=0.8, |
|
cond_tau=0.8, |
|
seed=0, |
|
) -> PIL.Image.Image: |
|
image = image.convert("RGB").resize((1024, 1024)) |
|
image = TF.to_tensor(image) > 0.5 |
|
image = TF.to_pil_image(image.to(torch.float32)) |
|
|
|
prompt, negative_prompt = apply_style(style, prompt, negative_prompt) |
|
|
|
generator = torch.Generator(device=device).manual_seed(seed) |
|
out = pipe( |
|
prompt=prompt, |
|
negative_prompt=negative_prompt, |
|
image=image, |
|
num_inference_steps=num_steps, |
|
generator=generator, |
|
guidance_scale=guidance_scale, |
|
adapter_conditioning_scale=adapter_conditioning_scale, |
|
cond_tau=cond_tau, |
|
).images[0] |
|
return out |
|
|
|
|
|
with gr.Blocks() as demo: |
|
gr.Markdown(DESCRIPTION) |
|
with gr.Row(): |
|
with gr.Column(): |
|
image = gr.Image( |
|
source="canvas", |
|
tool="sketch", |
|
type="pil", |
|
image_mode="1", |
|
invert_colors=True, |
|
shape=(1024, 1024), |
|
brush_radius=4, |
|
height=600, |
|
) |
|
prompt = gr.Textbox(label="Prompt") |
|
run_button = gr.Button("Run") |
|
with gr.Accordion("Advanced options", open=False): |
|
style = gr.Dropdown( |
|
choices=style_names, |
|
value=default_style, |
|
label="Style" |
|
) |
|
negative_prompt = gr.Textbox( |
|
label="Negative prompt", value="" |
|
) |
|
num_steps = gr.Slider( |
|
label="Number of steps", |
|
minimum=1, |
|
maximum=50, |
|
step=1, |
|
value=25, |
|
) |
|
guidance_scale = gr.Slider( |
|
label="Guidance scale", |
|
minimum=0.1, |
|
maximum=10.0, |
|
step=0.1, |
|
value=5, |
|
) |
|
adapter_conditioning_scale = gr.Slider( |
|
label="Adapter Conditioning Scale", |
|
minimum=0.5, |
|
maximum=1, |
|
step=0.1, |
|
value=.8, |
|
) |
|
cond_tau = gr.Slider( |
|
label="Fraction of timesteps for which adapter should be applied", |
|
minimum=0.5, |
|
maximum=1, |
|
step=0.1, |
|
value=.8, |
|
) |
|
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.Column(): |
|
result = gr.Image(label="Result", height=600) |
|
|
|
inputs = [ |
|
image, |
|
prompt, |
|
negative_prompt, |
|
style, |
|
num_steps, |
|
guidance_scale, |
|
adapter_conditioning_scale, |
|
cond_tau, |
|
seed, |
|
] |
|
prompt.submit( |
|
fn=randomize_seed_fn, |
|
inputs=[seed, randomize_seed], |
|
outputs=seed, |
|
queue=False, |
|
api_name=False, |
|
).then( |
|
fn=run, |
|
inputs=inputs, |
|
outputs=result, |
|
api_name=False, |
|
) |
|
run_button.click( |
|
fn=randomize_seed_fn, |
|
inputs=[seed, randomize_seed], |
|
outputs=seed, |
|
queue=False, |
|
api_name=False, |
|
).then( |
|
fn=run, |
|
inputs=inputs, |
|
outputs=result, |
|
api_name="run", |
|
) |
|
|
|
if __name__ == "__main__": |
|
demo.queue(max_size=20).launch() |
|
|