File size: 13,244 Bytes
e097f87
 
21ea13a
e097f87
 
21ea13a
e097f87
 
 
227fc7d
e097f87
 
 
 
 
a731861
3f3a332
 
 
e097f87
09b6bae
227fc7d
e097f87
 
3f3a332
e097f87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21ea13a
e097f87
 
 
 
 
 
 
 
 
 
3f3a332
e097f87
 
 
 
5ecd0a6
 
 
 
e097f87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21ea13a
e097f87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5ecd0a6
e097f87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21ea13a
e097f87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3f3a332
 
 
 
 
 
 
e097f87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
227fc7d
e097f87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
#!/usr/bin/env python
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 = """![Logo](https://raw.githubusercontent.com/PixArt-alpha/PixArt-alpha.github.io/master/static/images/pixart-lcm2.png)
        # PixArt-LCM 1024px
        #### [PixArt-Alpha 1024px](https://github.com/PixArt-alpha/PixArt-alpha) is a transformer-based text-to-image diffusion system trained on text embeddings from T5. This demo uses the [PixArt-alpha/PixArt-LCM-XL-2-1024-MS](https://huggingface.co/PixArt-alpha/PixArt-LCM-XL-2-1024-MS) checkpoint.
        #### [LCMs](https://github.com/luosiallen/latent-consistency-model) is a diffusion distillation method which predict PF-ODE's solution directly in latent space, achieving super fast inference with few steps.
        #### English prompts ONLY; 提示词仅限英文
        ### <span style='color: red;'> Don't want to queue or Don't get satisfied results? Try original demo: [PixArt-alpha](https://huggingface.co/spaces/PixArt-alpha/PixArt-alpha) [OpenXLab](https://openxlab.org.cn/apps/detail/PixArt-alpha/PixArt-alpha) or [Google Colab Demo](https://colab.research.google.com/drive/1jZ5UZXk7tcpTfVwnX33dDuefNMcnW9ME?usp=sharing).
        ### Feel free to change LCM inference steps in range [4, 10] according to your needs.
        """
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", "2048"))
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": "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": "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,
        seed: int = 0,
        width: int = 1024,
        height: int = 1024,
        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  # type: ignore
    prompt, negative_prompt = apply_style(style, prompt, negative_prompt)

    images = pipe(
        prompt=prompt,
        negative_prompt=negative_prompt,
        width=width,
        height=height,
        guidance_scale=0.,
        num_inference_steps=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 small cactus with a happy face in the Sahara desert.",
    "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, light pollution, cinematic atmosphere, art nouveau style, illustration art artwork by SenseiJaye, intricate detail.",
    "stars, water, brilliantly, gorgeous large scale scene, a little girl, in the style of dreamy realism, light gold and amber, blue and pink, brilliantly illuminated in the background.",
    "professional portrait photo of an anthropomorphic cat wearing fancy gentleman hat and jacket walking in autumn forest.",
    "beautiful lady, freckles, big smile, blue eyes, short ginger hair, dark makeup, wearing a floral blue vest top, soft light, dark grey background",
    "Spectacular Tiny World in the Transparent Jar On the Table, interior of the Great Hall, Elaborate, Carved Architecture, Anatomy, Symetrical, Geometric and Parameteric Details, Precision Flat line Details, Pattern, Dark fantasy, Dark errie mood and ineffably mysterious mood, Technical design, Intricate Ultra Detail, Ornate Detail, Stylized and Futuristic and Biomorphic Details, Architectural Concept, Low contrast Details, Cinematic Lighting, 8k, by moebius, Fullshot, Epic, Fullshot, Octane render, Unreal ,Photorealistic, Hyperrealism",
    "anthropomorphic profile of the white snow owl Crystal priestess , art deco painting, pretty and expressive eyes, ornate costume, mythical, ethereal, intricate, elaborate, hyperrealism, hyper detailed, 3D, 8K, Ultra Realistic, high octane, ultra resolution, amazing detail, perfection, In frame, photorealistic, cinematic lighting, visual clarity, shading , Lumen Reflections, Super-Resolution, gigapixel, color grading, retouch, enhanced, PBR, Blender, V-ray, Procreate, zBrush, Unreal Engine 5, cinematic, volumetric, dramatic, neon lighting, wide angle lens ,no digital painting blur",
    "The parametric hotel lobby is a sleek and modern space with plenty of natural light. The lobby is spacious and open with a variety of seating options. The front desk is a sleek white counter with a parametric design. The walls are a light blue color with parametric patterns. The floor is a light wood color with a parametric design. There are plenty of plants and flowers throughout the space. The overall effect is a calm and relaxing space. occlusion, moody, sunset, concept art, octane rendering, 8k, highly detailed, concept art, highly detailed, beautiful scenery, cinematic, beautiful light, hyperreal, octane render, hdr, long exposure, 8K, realistic, fog, moody, fire and explosions, smoke, 50mm f2.8",
]

with gr.Blocks(css="style.css") 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.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.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,
            )
        style_selection = gr.Radio(
            show_label=True,
            container=True,
            interactive=True,
            choices=STYLE_NAMES,
            value=DEFAULT_STYLE_NAME,
            label="Image Style",
        )
        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="LCM inference steps",
                minimum=1,
                maximum=30,
                step=1,
                value=6,
            )
    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,
            seed,
            width,
            height,
            inference_steps,
            randomize_seed,
        ],
        outputs=[result, seed],
        api_name="run",
    )


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