File size: 11,701 Bytes
c2c42ca
26b5270
81435cb
dca1cb5
61bc6a3
 
6da6b11
dca1cb5
 
 
440061e
 
 
 
 
 
 
 
 
 
 
 
a1f66f7
 
ec1fa2d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c2c42ca
aa5a24b
 
 
 
 
91dd651
c2c42ca
61bc6a3
 
 
 
c2c42ca
aa5a24b
 
 
 
 
 
 
 
 
 
 
 
 
61bc6a3
 
c2c42ca
61bc6a3
 
 
143f063
aa5a24b
 
 
 
 
 
 
 
 
 
 
 
61bc6a3
 
aa5a24b
91dd651
6da6b11
440061e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
302a450
440061e
 
 
 
 
 
 
 
 
 
 
 
302a450
440061e
 
 
 
 
 
 
 
 
 
 
 
302a450
440061e
 
 
 
 
 
 
 
 
 
 
 
302a450
440061e
 
 
 
 
 
 
 
 
 
 
 
302a450
143f063
b634b72
ddbaa70
 
 
 
 
 
 
 
61bc6a3
dc81866
d452942
c2c42ca
440061e
8e3d74a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c2c42ca
dc81866
440061e
dc81866
 
440061e
dc81866
 
440061e
dc81866
ec1fa2d
440061e
ec1fa2d
 
440061e
ec1fa2d
8e3d74a
bc87ae3
440061e
 
 
503dd68
440061e
09f0b4e
440061e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ddbaa70
 
 
09f0b4e
ddbaa70
440061e
09f0b4e
 
bc87ae3
5e64d98
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
import gradio as gr
from diffusers import StableDiffusionXLPipeline, UNet2DConditionModel, EulerDiscreteScheduler, LCMScheduler, AutoencoderKL,DiffusionPipeline
import torch
import numpy as np
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
import spaces
import os
import random
import uuid

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

MAX_SEED = np.iinfo(np.int32).max
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)

### RealVisXL V3 ###
RealVisXLv3_pipe = DiffusionPipeline.from_pretrained(
        "SG161222/RealVisXL_V3.0",
        torch_dtype=torch.float16,
        use_safetensors=True,
        add_watermarker=False,
        variant="fp16"
    )
RealVisXLv3_pipe.to("cuda")
### RealVisXL V4 ###
RealVisXLv4_pipe = DiffusionPipeline.from_pretrained(
        "SG161222/RealVisXL_V4.0",
        torch_dtype=torch.float16,
        use_safetensors=True,
        add_watermarker=False,
        variant="fp16"
    )
RealVisXLv4_pipe.to("cuda")
### SDXL Turbo #### 
pipe_turbo = StableDiffusionXLPipeline.from_pretrained("stabilityai/sdxl-turbo",
                                                       vae=vae,
                                                       torch_dtype=torch.float16,
                                                       variant="fp16"
                                                      )
pipe_turbo.to("cuda")

### SDXL Lightning ### 
base = "stabilityai/stable-diffusion-xl-base-1.0"
repo = "ByteDance/SDXL-Lightning"
ckpt = "sdxl_lightning_1step_unet_x0.safetensors" 

unet = UNet2DConditionModel.from_config(base, subfolder="unet").to(torch.float16)
unet.load_state_dict(load_file(hf_hub_download(repo, ckpt)))
pipe_lightning = StableDiffusionXLPipeline.from_pretrained(base,
                                                           unet=unet,
                                                           vae=vae,
                                                           text_encoder=pipe_turbo.text_encoder,
                                                           text_encoder_2=pipe_turbo.text_encoder_2,
                                                           tokenizer=pipe_turbo.tokenizer,
                                                           tokenizer_2=pipe_turbo.tokenizer_2,
                                                           torch_dtype=torch.float16,
                                                           variant="fp16"
                                                          )#.to("cuda")
del unet
pipe_lightning.scheduler = EulerDiscreteScheduler.from_config(pipe_lightning.scheduler.config, timestep_spacing="trailing", prediction_type="sample")
pipe_lightning.to("cuda")

### Hyper SDXL ### 
repo_name = "ByteDance/Hyper-SD"
ckpt_name = "Hyper-SDXL-1step-Unet.safetensors"

unet = UNet2DConditionModel.from_config(base, subfolder="unet").to(torch.float16)
unet.load_state_dict(load_file(hf_hub_download(repo_name, ckpt_name)))
pipe_hyper = StableDiffusionXLPipeline.from_pretrained(base,
                                                       unet=unet,
                                                       vae=vae,
                                                       text_encoder=pipe_turbo.text_encoder,
                                                       text_encoder_2=pipe_turbo.text_encoder_2,
                                                       tokenizer=pipe_turbo.tokenizer,
                                                       tokenizer_2=pipe_turbo.tokenizer_2,
                                                       torch_dtype=torch.float16,
                                                       variant="fp16"
                                                      )#.to("cuda")
pipe_hyper.scheduler = LCMScheduler.from_config(pipe_hyper.scheduler.config)
pipe_hyper.to("cuda")
del unet

@spaces.GPU
def run_comparison(prompt: str,
    negative_prompt: str = "",
    use_negative_prompt: bool = False,
    num_inference_steps: int = 30,
    num_images_per_prompt: int = 2,
    seed: int = 0,
    width: int = 1024,
    height: int = 1024,
    guidance_scale: float = 3,
    randomize_seed: bool = False,
    progress=gr.Progress(track_tqdm=True),
):
    seed = int(randomize_seed_fn(seed, randomize_seed))
    if not use_negative_prompt:
        negative_prompt = ""
    image_turbo=pipe_turbo(prompt=prompt,
        negative_prompt=negative_prompt,
        width=width,
        height=height,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        num_images_per_prompt=num_images_per_prompt,
        cross_attention_kwargs={"scale": 0.65},
        output_type="pil",
        ).images
    image_paths = [save_image(img) for img in images]
    return image_paths, seed
    yield image_turbo, None, None, None, None
    image_lightning=pipe_lightning(prompt=prompt,
        negative_prompt=negative_prompt,
        width=width,
        height=height,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        num_images_per_prompt=num_images_per_prompt,
        cross_attention_kwargs={"scale": 0.65},
        output_type="pil",
        ).images
    image_paths = [save_image(img) for img in images]
    return image_paths, seed
    yield image_turbo, image_lightning, None, None, None
    image_hyper=pipe_hyper(prompt=prompt,
        negative_prompt=negative_prompt,
        width=width,
        height=height,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        num_images_per_prompt=num_images_per_prompt,
        cross_attention_kwargs={"scale": 0.65},
        output_type="pil",
        ).images
    image_paths = [save_image(img) for img in images]
    return image_paths, seed
    yield image_turbo, image_lightning, image_hyper, None, None
    image_r3=RealVisXLv3_pipe(prompt=prompt,
        negative_prompt=negative_prompt,
        width=width,
        height=height,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        num_images_per_prompt=num_images_per_prompt,
        cross_attention_kwargs={"scale": 0.65},
        output_type="pil",
        ).images
    image_paths = [save_image(img) for img in images]
    return image_paths, seed
    yield image_turbo, image_lightning, image_hyper,image_r3, None
    image_r4=RealVisXLv4_pipe(prompt=prompt,
        negative_prompt=negative_prompt,
        width=width,
        height=height,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        num_images_per_prompt=num_images_per_prompt,
        cross_attention_kwargs={"scale": 0.65},
        output_type="pil",
        ).images
    image_paths = [save_image(img) for img in images]
    return image_paths, seed
    yield image_turbo, image_lightning, image_hyper,image_r3, image_r4

examples = ["A dignified beaver wearing glasses, a vest, and colorful neck tie.",
"The spirit of a tamagotchi wandering in the city of Barcelona",
"an ornate, high-backed mahogany chair with a red cushion",
"a sketch of a camel next to a stream",
"a delicate porcelain teacup sits on a saucer, its surface adorned with intricate blue patterns",
"a baby swan grafitti",
"A bald eagle made of chocolate powder, mango, and whipped cream"
]

with gr.Blocks() as demo:
    gr.Markdown("## One step SDXL comparison 🦶")
    gr.Markdown('Compare SDXL variants and distillations able to generate images in a single diffusion step')
    prompt = gr.Textbox(label="Prompt")
    run = gr.Button("Run")
    with gr.Accordion("Advanced options", open=False):
        use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=True)
        negative_prompt = gr.Text(
            label="Negative prompt",
            lines=4,
            max_lines=6,
            value="""(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, (NSFW:1.25)""",
            placeholder="Enter a negative prompt",
            visible=True,
        )
        with gr.Row():
            num_inference_steps = gr.Slider(
                label="Steps",
                minimum=10,
                maximum=60,
                step=1,
                value=30,
            )
        with gr.Row():
            num_images_per_prompt = gr.Slider(
                label="Images",
                minimum=1,
                maximum=5,
                step=1,
                value=2,
            )
        seed = gr.Slider(
            label="Seed",
            minimum=0,
            maximum=MAX_SEED,
            step=1,
            value=0,
            visible=True
        )
        randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
        with gr.Row(visible=True):
            width = gr.Slider(
                label="Width",
                minimum=512,
                maximum=2048,
                step=8,
                value=1024,
            )
            height = gr.Slider(
                label="Height",
                minimum=512,
                maximum=2048,
                step=8,
                value=1024,
            )
        with gr.Row():
            guidance_scale = gr.Slider(
                label="Guidance Scale",
                minimum=0.1,
                maximum=20.0,
                step=0.1,
                value=6,
            )

    with gr.Row():
        with gr.Column():
            image_turbo = gr.Gallery(label="SDXL Turbo",columns=1, preview=True,)
            gr.Markdown("## [SDXL Turbo](https://huggingface.co/stabilityai/sdxl-turbo)")
        with gr.Column():
            image_lightning = gr.Gallery(label="SDXL Lightning",columns=1, preview=True,)
            gr.Markdown("## [SDXL Lightning](https://huggingface.co/ByteDance/SDXL-Lightning)")
        with gr.Column():
            image_hyper = gr.Gallery(label="Hyper SDXL",columns=1, preview=True,)
            gr.Markdown("## [Hyper SDXL](https://huggingface.co/ByteDance/Hyper-SD)")
        with gr.Column():
            image_r3 = gr.Gallery(label="RealVisXL V3",columns=1, preview=True,)
            gr.Markdown("## [RealVisXL V3](https://huggingface.co)")
        with gr.Column():
            image_r4 = gr.Gallery(label="RealVisXL V4",columns=1, preview=True,)
            gr.Markdown("## [RealVisXL V3](https://huggingface.co)")
    image_outputs = [image_turbo, image_lightning, image_hyper, image_r3, image_r4]
    gr.on(
        triggers=[
            prompt.submit,
            negative_prompt.submit,
            run.click,
        ],
        fn=run_comparison,
        inputs=[
            prompt,
            negative_prompt,
            use_negative_prompt,
            num_inference_steps,
            num_images_per_prompt,
            seed,
            width,
            height,
            guidance_scale,
            randomize_seed,
        ],
        outputs=[image_outputs, seed],
        api_name="run",
    )
    use_negative_prompt.change(
        fn=lambda x: gr.update(visible=x),
        inputs=use_negative_prompt,
        outputs=negative_prompt,
        api_name=False,
    )
    gr.Examples(
        examples=examples,
        fn=run_comparison,
        inputs=prompt,
        outputs=[image_outputs, seed],
        cache_examples=False,
        run_on_click=True
    )
demo.launch()