File size: 8,536 Bytes
cc54eed
 
 
 
 
 
 
 
 
 
 
d5a21dc
cc54eed
 
 
 
 
 
 
 
 
 
 
52ef426
cc54eed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c1e1bbb
 
cc54eed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0b25929
cc54eed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d5a21dc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cc54eed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52ef426
cc54eed
 
52ef426
cc54eed
 
 
 
 
 
 
 
 
 
 
 
 
 
52ef426
cc54eed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
945caaf
cc54eed
 
 
 
 
 
 
 
 
 
 
 
 
d5a21dc
 
 
 
cc54eed
 
ab2e71e
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
import os
import random
import gradio as gr
import numpy as np
import PIL.Image
import torch
from typing import List
from diffusers.utils import numpy_to_pil
from diffusers import StableCascadeDecoderPipeline, StableCascadePriorPipeline
from diffusers.pipelines.wuerstchen import DEFAULT_STAGE_C_TIMESTEPS

#import user_history

os.environ['TOKENIZERS_PARALLELISM'] = 'false'

DESCRIPTION = "# Stable Cascade"
#DESCRIPTION += "\n<p style=\"text-align: center\"><a href='https://huggingface.co/warp-ai/wuerstchen' target='_blank'>Würstchen</a> is a new fast and efficient high resolution text-to-image architecture and model</p>"
if not torch.cuda.is_available():
    DESCRIPTION += "\n<p>Running on CPU 🥶</p>"

MAX_SEED = np.iinfo(np.int32).max
CACHE_EXAMPLES = torch.cuda.is_available() and os.getenv("CACHE_EXAMPLES") == "1"
MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "1536"))
USE_TORCH_COMPILE = True
ENABLE_CPU_OFFLOAD = os.getenv("ENABLE_CPU_OFFLOAD") == "1"

dtype = torch.float16
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
if torch.cuda.is_available():
    prior_pipeline = StableCascadePriorPipeline.from_pretrained("diffusers/StableCascade-prior", torch_dtype=torch.bfloat16).to("cuda")
    decoder_pipeline = StableCascadeDecoderPipeline.from_pretrained("diffusers/StableCascade-decoder",  torch_dtype=torch.bfloat16).to("cuda") 

    if ENABLE_CPU_OFFLOAD:
        prior_pipeline.enable_model_cpu_offload()
        decoder_pipeline.enable_model_cpu_offload()
    else:
        prior_pipeline.to(device)
        decoder_pipeline.to(device)

    if USE_TORCH_COMPILE:
        prior_pipeline.prior = torch.compile(prior_pipeline.prior, mode="reduce-overhead", fullgraph=True)
        decoder_pipeline.decoder = torch.compile(decoder_pipeline.decoder, mode="reduce-overhead", fullgraph=True)

    if PREVIEW_IMAGES:
        pass
    #    previewer = Previewer()
    #    previewer.load_state_dict(torch.load("previewer/text2img_wurstchen_b_v1_previewer_100k.pt")["state_dict"])
    #    previewer.eval().requires_grad_(False).to(device).to(dtype)

    #    def callback_prior(i, t, latents):
    #        output = previewer(latents)
    #        output = numpy_to_pil(output.clamp(0, 1).permute(0, 2, 3, 1).cpu().numpy())
    #        return output

    else:
        previewer = None
        callback_prior = None
else:
    prior_pipeline = None
    decoder_pipeline = None


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 = "",
    seed: int = 0,
    width: int = 1024,
    height: int = 1024,
    prior_num_inference_steps: int = 60,
    # prior_timesteps: List[float] = None,
    prior_guidance_scale: float = 4.0,
    decoder_num_inference_steps: int = 12,
    # decoder_timesteps: List[float] = None,
    decoder_guidance_scale: float = 0.0,
    num_images_per_prompt: int = 2,
    #profile: gr.OAuthProfile | None = None,
) -> PIL.Image.Image:
    generator = torch.Generator().manual_seed(seed)

    prior_output = prior_pipeline(
        prompt=prompt,
        height=height,
        width=width,
        timesteps=DEFAULT_STAGE_C_TIMESTEPS,
        negative_prompt=negative_prompt,
        guidance_scale=prior_guidance_scale,
        num_images_per_prompt=num_images_per_prompt,
        generator=generator,
        callback=callback_prior,
    )

    #if PREVIEW_IMAGES:
    #    for _ in range(len(DEFAULT_STAGE_C_TIMESTEPS)):
    #        r = next(prior_output)
    #        if isinstance(r, list):
    #            yield r
    #    prior_output = r

    decoder_output = decoder_pipeline(
        image_embeddings=prior_output.image_embeddings,
        prompt=prompt,
        num_inference_steps=decoder_num_inference_steps,
        # timesteps=decoder_timesteps,
        guidance_scale=decoder_guidance_scale,
        negative_prompt=negative_prompt,
        generator=generator,
        output_type="pil",
    ).images

    # Save images
    #for image in decoder_output:
    #    user_history.save_image(
    #        profile=profile,
    #        image=image,
    #        label=prompt,
    #        metadata={
    #            "negative_prompt": negative_prompt,
    #            "seed": seed,
    #            "width": width,
    #            "height": height,
    #            "prior_guidance_scale": prior_guidance_scale,
    #            "decoder_num_inference_steps": decoder_num_inference_steps,
    #            "decoder_guidance_scale": decoder_guidance_scale,
    #            "num_images_per_prompt": num_images_per_prompt,
    #        },
    #    )

    yield decoder_output


examples = [
    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
    "An astronaut riding a green horse",
]

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.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", show_label=False)
    with gr.Accordion("Advanced options", open=False):
        negative_prompt = gr.Text(
            label="Negative prompt",
            max_lines=1,
            placeholder="Enter a Negative Prompt",
        )

        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():
            width = gr.Slider(
                label="Width",
                minimum=1024,
                maximum=MAX_IMAGE_SIZE,
                step=512,
                value=1024,
            )
            height = gr.Slider(
                label="Height",
                minimum=1024,
                maximum=MAX_IMAGE_SIZE,
                step=512,
                value=1024,
            )
            num_images_per_prompt = gr.Slider(
                label="Number of Images",
                minimum=1,
                maximum=2,
                step=1,
                value=2,
            )
        with gr.Row():
            prior_guidance_scale = gr.Slider(
                label="Prior Guidance Scale",
                minimum=0,
                maximum=20,
                step=0.1,
                value=4.0,
            )
            prior_num_inference_steps = gr.Slider(
                label="Prior Inference Steps",
                minimum=10,
                maximum=30,
                step=1,
                value=25,
            )

            decoder_guidance_scale = gr.Slider(
                label="Decoder Guidance Scale",
                minimum=0,
                maximum=0,
                step=0.1,
                value=0.0,
            )
            decoder_num_inference_steps = gr.Slider(
                label="Decoder Inference Steps",
                minimum=4,
                maximum=12,
                step=1,
                value=10,
            )

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

    inputs = [
            prompt,
            negative_prompt,
            seed,
            width,
            height,
            prior_num_inference_steps,
            # prior_timesteps,
            prior_guidance_scale,
            decoder_num_inference_steps,
            # decoder_timesteps,
            decoder_guidance_scale,
            num_images_per_prompt,
    ]
    gr.on(
        triggers=[prompt.submit, negative_prompt.submit, run_button.click],
        fn=randomize_seed_fn,
        inputs=[seed, randomize_seed],
        outputs=seed,
        queue=False,
        api_name=False,
    ).then(
        fn=generate,
        inputs=inputs,
        outputs=result,
        api_name="run",
    )
    
with gr.Blocks(css="style.css") as demo_with_history:
    #with gr.Tab("App"):
    demo.render()
    #with gr.Tab("Past generations"):
    #    user_history.render()

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