File size: 12,244 Bytes
df86cb4
 
 
d2cbb30
df86cb4
 
 
d2cbb30
df86cb4
 
 
 
 
7f79770
 
 
d29f160
df86cb4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45b7208
 
 
df86cb4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7f79770
df86cb4
 
4b27876
 
 
 
 
 
df86cb4
 
d2cbb30
 
 
accee48
 
df86cb4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eaa59c1
 
df86cb4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d2cbb30
 
 
df86cb4
 
 
 
 
 
 
d2cbb30
4b27876
df86cb4
 
 
 
 
 
69b393a
df86cb4
 
 
d2cbb30
df86cb4
 
 
 
eaa59c1
df86cb4
 
 
 
 
45b7208
9dfd02f
 
 
 
 
 
 
 
 
df86cb4
 
9dabfc7
df86cb4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
acf4855
df86cb4
 
 
 
d2cbb30
 
 
 
 
 
 
df86cb4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d2cbb30
df86cb4
 
 
 
 
 
d2cbb30
df86cb4
d2cbb30
 
 
 
 
 
 
 
df86cb4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f35fd99
 
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
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
from __future__ import annotations
import os
import random
import uuid
import gradio as gr
import numpy as np
import uuid
from diffusers import PixArtAlphaPipeline, LCMScheduler
import torch
from typing import Tuple
from datetime import datetime


DESCRIPTION = """ # Instant Image
        ### Super fast text to Image Generator.
        ### <span style='color: red;'>You may change the steps from 9 to 15, if you didn't get satisfied results.
        ### First Image processing takes time then images generate faster.
        """
if not torch.cuda.is_available():
    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"

MAX_SEED = np.iinfo(np.int32).max
CACHE_EXAMPLES = torch.cuda.is_available() and os.getenv("CACHE_EXAMPLES", "1") == "1"
MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "6000"))
USE_TORCH_COMPILE = os.getenv("USE_TORCH_COMPILE", "0") == "1"
ENABLE_CPU_OFFLOAD = os.getenv("ENABLE_CPU_OFFLOAD", "0") == "1"

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")


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": "Realistic",
        "prompt": "Photorealistic {prompt} . Ulta-realistic, professional, 4k, highly detailed",
        "negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, disfigured",
    },
    {
        "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": "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",
    },
    {
        "name": "Digital Art",
        "prompt": "concept art {prompt} . digital artwork, illustrative, painterly, matte painting, highly detailed",
        "negative_prompt": "photo, photorealistic, realism, 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": "3D Model",
        "prompt": "professional 3d model {prompt} . octane render, highly detailed, volumetric, dramatic lighting",
        "negative_prompt": "ugly, deformed, noisy, low poly, blurry, painting",
    },
]


styles = {k["name"]: (k["prompt"], k["negative_prompt"]) for k in style_list}
STYLE_NAMES = list(styles.keys())
DEFAULT_STYLE_NAME = "(No style)"
NUM_IMAGES_PER_PROMPT = 1

def apply_style(style_name: str, positive: str, negative: str = "") -> Tuple[str, str]:
    p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME])
    if not negative:
        negative = ""
    return p.replace("{prompt}", positive), n + negative

if torch.cuda.is_available():

    pipe = PixArtAlphaPipeline.from_pretrained(
        "PixArt-alpha/PixArt-LCM-XL-2-1024-MS",
        torch_dtype=torch.float16,
        use_safetensors=True,
    )

    if os.getenv('CONSISTENCY_DECODER', False):
        print("Using DALL-E 3 Consistency Decoder")
        pipe.vae = ConsistencyDecoderVAE.from_pretrained("openai/consistency-decoder", torch_dtype=torch.float16)

    if ENABLE_CPU_OFFLOAD:
        pipe.enable_model_cpu_offload()
    else:
        pipe.to(device)
        print("Loaded on Device!")

    # speed-up T5
    pipe.text_encoder.to_bettertransformer()

    if USE_TORCH_COMPILE:
        pipe.transformer = torch.compile(pipe.transformer, mode="reduce-overhead", fullgraph=True)
        print("Model Compiled!")

def save_image(img):
    unique_name = str(uuid.uuid4()) + ".png"
    img.save(unique_name)
    return unique_name

def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    return seed

def generate(
        prompt: str,
        negative_prompt: str = "",
        style: str = DEFAULT_STYLE_NAME,
        use_negative_prompt: bool = False,
        num_imgs: int = 1,
        seed: int = 0,
        width: int = 1024,
        height: int = 1024,
        num_inference_steps: int = 4,
        randomize_seed: bool = False,
        use_resolution_binning: bool = True,
        progress=gr.Progress(track_tqdm=True),
):
    seed = int(randomize_seed_fn(seed, randomize_seed))
    generator = torch.Generator().manual_seed(seed)

if not use_negative_prompt:
        negative_prompt = None
    prompt, negative_prompt = apply_style(style, prompt, negative_prompt)

    images = pipe(
        prompt=prompt,
        width=width,
        height=height,
        negative_prompt=negative_prompt,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        generator=generator,
        num_images_per_prompt=NUM_IMAGES_PER_PROMPT,
        use_resolution_binning=use_resolution_binning,
        output_type="pil",
    ).images

    image_paths = [save_image(img) for img in images]
    print(image_paths)
    return image_paths, seed


examples = [
    "A Monkey with a happy face in the Sahara desert.",
    "Eiffel Tower was Made up of ICE to look like a cloud, with the bell tower at the top of the building.",
    "3D small, round, fluffy creature with big, expressive eyes explores a vibrant, enchanted forest. The creature, a whimsical blend of a rabbit and a squirrel, has soft blue fur and a bushy, striped tail. It hops along a sparkling stream, its eyes wide with wonder. The forest is alive with magical elements: flowers that glow and change colors, trees with leaves in shades of purple and silver, and small floating lights that resemble fireflies. The creature stops to interact playfully with a group of tiny, fairy-like beings dancing around a mushroom ring. The creature looks up in awe at a large, glowing tree that seems to be the heart of the forest.",
    "Color photo of a corgi made of transparent glass, standing on the riverside in Yosemite National Park.",
    "A close-up photo of a woman. She wore a blue coat with a gray dress underneath. She has blue eyes and blond hair, and wears a pair of earrings. Behind are blurred city buildings and streets.",
    "A litter of golden retriever puppies playing in the snow. Their heads pop out of the snow, covered in.",
    "a handsome young boy in the middle with sky color background wearing eye glasses, it's super detailed with anime style, it's a portrait with delicated eyes and nice looking face",
    "an astronaut sitting in a diner, eating fries, cinematic, analog film",
    "Pirate ship trapped in a cosmic maelstrom nebula, rendered in cosmic beach whirlpool engine, volumetric lighting, spectacular, ambient lights, intricate detail.",
    "professional portrait photo of an anthropomorphic cat wearing fancy gentleman hat and jacket walking in autumn forest.",
]

with gr.Blocks() as demo:
    gr.Markdown(DESCRIPTION)
    gr.DuplicateButton(
        value="Duplicate Space for private use",
        elem_id="duplicate-button",
        visible=os.getenv("SHOW_DUPLICATE_BUTTON") == "1",
    )
    with gr.Row(equal_height=False):
        with gr.Group():
            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.Gallery(label="Result", columns=NUM_IMAGES_PER_PROMPT,  show_label=False)
        # with gr.Accordion("Advanced options", open=False):
        with gr.Group():
            with gr.Row():
                use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=False, visible=True)
                 negative_prompt = gr.Text(
                label="Negative prompt",
                max_lines=1,
                placeholder="Enter a negative prompt",
                visible=True,
            )
              
                num_imgs = gr.Slider(
                    label="Num Images",
                    minimum=1,
                    maximum=8,
                    step=1,
                    value=1,
                )
            style_selection = gr.Radio(
                show_label=True,
                container=True,
                interactive=True,
                choices=STYLE_NAMES,
                value=DEFAULT_STYLE_NAME,
                label="Image Style",
            )
            negative_prompt = gr.Text(
                label="Negative prompt",
                max_lines=1,
                placeholder="Enter a negative prompt",
                visible=True,
            )
            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(visible=True):
                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():
            inference_steps = gr.Slider(
                label="Steps",
                minimum=1,
                maximum=30,
                step=1,
                value=6,
            )  value=9,
                )

    gr.Examples(
        examples=examples,
        inputs=prompt,
        outputs=[result, seed],
        fn=generate,
        cache_examples=CACHE_EXAMPLES,
    )

    use_negative_prompt.change(
        fn=lambda x: gr.update(visible=x),
        inputs=use_negative_prompt,
        outputs=negative_prompt,
        api_name=False,
    )

    gr.on(
        triggers=[
            prompt.submit,
            negative_prompt.submit,
            run_button.click,
        ],
        fn=generate,
        inputs=[
            prompt,
            negative_prompt,
            style_selection,
            use_negative_prompt,
            num_imgs,
            seed,
            width,
            height,
            schedule,
            dpms_guidance_scale,
            dpms_inference_steps,
            randomize_seed,
        ],
        outputs=[result, seed],
        api_name="run",
    )

if __name__ == "__main__":
    demo.queue(max_size=20).launch()
    # demo.queue(max_size=20).launch(server_name="0.0.0.0", server_port=11900, debug=True)