File size: 9,529 Bytes
448d919
 
6bec03c
448d919
 
 
 
 
 
0ba1071
910b076
 
 
 
 
 
448d919
b19bfb9
b011089
 
448d919
 
 
 
910b076
ae76338
 
 
 
 
ebd0807
092ceda
ebd0807
910b076
ebd0807
 
092ceda
ebd0807
910b076
ebd0807
 
092ceda
ebd0807
910b076
ebd0807
 
092ceda
ebd0807
910b076
ebd0807
 
092ceda
ebd0807
910b076
ebd0807
 
092ceda
ebd0807
910b076
ebd0807
 
092ceda
ebd0807
910b076
ebd0807
ae76338
 
 
 
 
 
 
 
 
 
ebd0807
 
910b076
ae76338
 
ebd0807
 
811ffbe
ae76338
910b076
 
ebd0807
448d919
 
 
910b076
 
 
edb91ec
448d919
 
112de75
448d919
112de75
448d919
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ae76338
edb2f4b
 
 
ae76338
edb2f4b
ae76338
448d919
a679a71
0ba1071
 
448d919
edb2f4b
59db96e
448d919
 
 
 
 
 
 
 
0ba1071
ae76338
448d919
5898cfd
448d919
 
8513dc8
70b82cd
6bec03c
 
 
 
 
 
448d919
 
206fc98
 
 
 
 
a679a71
206fc98
 
 
45a9c8b
206fc98
 
ae76338
206fc98
448d919
ae76338
 
 
 
448d919
 
 
21e8f52
448d919
21e8f52
448d919
 
 
 
21e8f52
448d919
21e8f52
448d919
6759e22
ae76338
6759e22
 
 
910b076
0df770e
ae76338
 
 
0df770e
 
 
910b076
6759e22
448d919
 
 
 
 
 
 
 
 
46e57d1
448d919
 
 
 
 
59db96e
448d919
 
6759e22
ae76338
448d919
 
 
 
 
 
 
 
 
 
 
 
 
 
651aca2
 
 
 
 
 
 
 
 
 
 
 
448d919
 
 
 
 
 
 
 
 
 
ae76338
448d919
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
#!/usr/bin/env python

import os
import random

import gradio as gr
import numpy as np
import PIL.Image
import torch
import torchvision.transforms.functional as TF
from diffusers import (
    AutoencoderKL,
    EulerAncestralDiscreteScheduler,
    StableDiffusionXLAdapterPipeline,
    T2IAdapter,
)

DESCRIPTION = '''# Doodly - T2I-Adapter-SDXL **Sketch**
To try out all the [6 T2I-Adapter](https://huggingface.co/collections/TencentARC/t2i-adapter-sdxl-64fac9cbf393f30370eeb02f) released for SDXL, [click here](https://huggingface.co/spaces/TencentARC/T2I-Adapter-SDXL)
'''

if not torch.cuda.is_available():
    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"

style_list = [
    {
        "name": "(No style)",
        "prompt": "{prompt}",
        "negative_prompt": "",
    },
    {
        "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",
    },
    {
        "name": "Neonpunk",
        "prompt": "neonpunk style {prompt} . cyberpunk, vaporwave, neon, vibes, vibrant, stunningly beautiful, crisp, detailed, sleek, ultramodern, magenta highlights, dark purple shadows, high contrast, cinematic, ultra detailed, intricate, professional",
        "negative_prompt": "painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured",
    },
    {
        "name": "Manga",
        "prompt": "manga style {prompt} . vibrant, high-energy, detailed, iconic, Japanese comic style",
        "negative_prompt": "ugly, deformed, noisy, blurry, low contrast, realism, photorealistic, Western comic style",
    },
]

styles = {k["name"]: (k["prompt"], k["negative_prompt"]) for k in style_list}
STYLE_NAMES = list(styles.keys())
DEFAULT_STYLE_NAME = "(No style)"


def apply_style(style_name: str, positive: str, negative: str = "") -> tuple[str, str]:
    p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME])
    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_name: str = DEFAULT_STYLE_NAME,
    num_steps: int = 25,
    guidance_scale: float = 5,
    adapter_conditioning_scale: float = 0.8,
    adapter_conditioning_factor: float = 0.8,
    seed: int = 0,
    progress=gr.Progress(track_tqdm=True),
) -> PIL.Image.Image:
    image = image.convert("RGB")
    image = TF.to_tensor(image) > 0.5
    image = TF.to_pil_image(image.to(torch.float32))

    prompt, negative_prompt = apply_style(style_name, 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,
        adapter_conditioning_factor=adapter_conditioning_factor,
    ).images[0]
    return out


with gr.Blocks(css="style.css") as demo:
    gr.Markdown(DESCRIPTION, elem_id="description")
    gr.DuplicateButton(
        value="Duplicate Space for private use",
        elem_id="duplicate-button",
        visible=os.getenv("SHOW_DUPLICATE_BUTTON") == "1",
    )

    with gr.Row():
        with gr.Column():
            with gr.Group():
                image = gr.Image(
                    source="canvas",
                    tool="sketch",
                    type="pil",
                    image_mode="L",
                    invert_colors=True,
                    shape=(1024, 1024),
                    brush_radius=4,
                    height=440,
                )
                prompt = gr.Textbox(label="Prompt")
                style = gr.Dropdown(label="Style", choices=STYLE_NAMES, value=DEFAULT_STYLE_NAME)
                run_button = gr.Button("Run")
            with gr.Accordion("Advanced options", open=False):
                negative_prompt = gr.Textbox(
                    label="Negative prompt",
                    value=" extra digit, fewer digits, cropped, worst quality, low quality, glitch, deformed, mutated, ugly, disfigured",
                )
                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=0.8,
                )
                adapter_conditioning_factor = gr.Slider(
                    label="Adapter conditioning factor",
                    info="Fraction of timesteps for which adapter should be applied",
                    minimum=0.5,
                    maximum=1,
                    step=0.1,
                    value=0.8,
                )
                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=400)

    inputs = [
        image,
        prompt,
        negative_prompt,
        style,
        num_steps,
        guidance_scale,
        adapter_conditioning_scale,
        adapter_conditioning_factor,
        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,
    )
    negative_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=False,
    )

if __name__ == "__main__":
    demo.queue(max_size=20).launch()