Spaces:
Running
on
Zero
Running
on
Zero
File size: 7,900 Bytes
e4014ea 8166181 e4014ea 8166181 e4014ea 8166181 e4014ea 8166181 e4014ea 8166181 e4014ea 8166181 e4014ea 8166181 e4014ea 8166181 e4014ea 8166181 e4014ea 8166181 e4014ea 8166181 e4014ea |
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 |
import gradio as gr
import numpy as np
import random
import spaces
from diffusers import AuraFlowPipeline
import torch
from gradio_imageslider import ImageSlider
device = "cuda" if torch.cuda.is_available() else "cpu"
#torch.set_float32_matmul_precision("high")
#torch._inductor.config.conv_1x1_as_mm = True
#torch._inductor.config.coordinate_descent_tuning = True
#torch._inductor.config.epilogue_fusion = False
#torch._inductor.config.coordinate_descent_check_all_directions = True
#pipe_v1 = AuraFlowPipeline.from_pretrained(
# "fal/AuraFlow",
# torch_dtype=torch.float16
#).to("cuda")
pipe_v2 = AuraFlowPipeline.from_pretrained(
"fal/AuraFlow-v0.2",
torch_dtype=torch.float16
).to("cuda")
pipe = AuraFlowPipeline.from_pretrained(
"fal/AuraFlow-v0.3",
torch_dtype=torch.float16
).to("cuda")
#pipe.transformer.to(memory_format=torch.channels_last)
#pipe.transformer = torch.compile(pipe.transformer, mode="reduce-overhead", fullgraph=True)
#pipe.transformer.to(memory_format=torch.channels_last)
#pipe.vae.to(memory_format=torch.channels_last)
#pipe.transformer = torch.compile(pipe.transformer, mode="max-autotune", fullgraph=True)
#pipe.vae.decode = torch.compile(pipe.vae.decode, mode="max-autotune", fullgraph=True)
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024
@spaces.GPU()
def infer_example(prompt, negative_prompt="", seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=5.0, num_inference_steps=28, model_version="0.2", comparison_mode=False, progress=gr.Progress(track_tqdm=True)):
generator = torch.Generator().manual_seed(seed)
image = pipe(
prompt = prompt,
negative_prompt = negative_prompt,
width = width,
height = height,
guidance_scale = guidance_scale,
num_inference_steps = num_inference_steps,
generator = generator
).images[0]
return image, seed
@spaces.GPU(duration=95)
def infer(prompt,
negative_prompt="",
seed=42,
randomize_seed=False,
width=1024,
height=1024,
guidance_scale=5.0,
num_inference_steps=28,
model_version="0.3",
comparison_mode=False,
progress=gr.Progress(track_tqdm=True)
):
if randomize_seed:
seed = random.randint(0, MAX_SEED)
generator = torch.Generator().manual_seed(seed)
if(comparison_mode):
image_1 = pipe_v2(
prompt = prompt,
negative_prompt = negative_prompt,
width=width,
height=height,
guidance_scale = guidance_scale,
num_inference_steps = num_inference_steps,
generator = generator
).images[0]
generator = torch.Generator().manual_seed(seed)
image_2 = pipe(
prompt = prompt,
negative_prompt = negative_prompt,
width=width,
height=height,
guidance_scale = guidance_scale,
num_inference_steps = num_inference_steps,
generator = generator
).images[0]
return gr.update(visible=False), gr.update(visible=True, value=(image_1, image_2)), seed
if(model_version == "0.1"):
image = pipe_v1(
prompt = prompt,
negative_prompt = negative_prompt,
width=width,
height=height,
guidance_scale = guidance_scale,
num_inference_steps = num_inference_steps,
generator = generator
).images[0]
elif(model_version == "0.2"):
image = pipe_v2(
prompt = prompt,
negative_prompt = negative_prompt,
width=width,
height=height,
guidance_scale = guidance_scale,
num_inference_steps = num_inference_steps,
generator = generator
).images[0]
else:
image = pipe(
prompt = prompt,
negative_prompt = negative_prompt,
width=width,
height=height,
guidance_scale = guidance_scale,
num_inference_steps = num_inference_steps,
generator = generator
).images[0]
return gr.update(visible=True, value=image), gr.update(visible=False), seed
examples = [
"A photo of a lavender cat",
"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
"An astronaut riding a green horse",
"A delicious ceviche cheesecake slice",
]
css="""
#col-container {
margin: 0 auto;
max-width: 520px;
}
"""
with gr.Blocks(css=css) as demo:
with gr.Column(elem_id="col-container"):
gr.Markdown(f"""
# AuraFlow 0.3
Demo of the [AuraFlow 0.3](https://huggingface.co/fal/AuraFlow-v0.3) 6.8B parameters open source diffusion transformer model
[[blog](https://blog.fal.ai/auraflow/)] [[model](https://huggingface.co/fal/AuraFlow)] [[fal](https://fal.ai/models/fal-ai/aura-flow)]
""")
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.Image(label="Result", show_label=False)
result_compare = ImageSlider(visible=False, label="Left 0.2, Right 0.3")
comparison_mode = gr.Checkbox(label="Comparison mode", info="Compare v0.2 with v0.3", value=False)
with gr.Accordion("Advanced Settings", open=False):
model_version = gr.Dropdown(
["0.2", "0.3"], label="Model version", value="0.3"
)
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=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():
guidance_scale = gr.Slider(
label="Guidance scale",
minimum=0.0,
maximum=10.0,
step=0.1,
value=5.0,
)
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=50,
step=1,
value=28,
)
gr.Examples(
examples = examples,
fn = infer_example,
inputs = [prompt],
outputs = [result, seed],
cache_examples="lazy"
)
gr.on(
triggers=[run_button.click, prompt.submit, negative_prompt.submit],
fn = infer,
inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, model_version, comparison_mode],
outputs = [result, result_compare, seed]
)
demo.queue().launch() |