File size: 4,416 Bytes
8ccf632 eb27b70 2d69d95 06f0278 8ccf632 2d69d95 8ccf632 06f0278 2d69d95 8ccf632 2d69d95 54192f0 2d69d95 8ccf632 2d69d95 06f0278 2d69d95 8ccf632 06f0278 8ccf632 2d69d95 8ccf632 e2944a6 8ccf632 2d69d95 8ccf632 2d69d95 8ccf632 2d69d95 8ccf632 9aa8809 |
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 |
import gradio as gr
import numpy as np
import random
import spaces
import torch
from diffusers import DiffusionPipeline
from transformers import CLIPTokenizer
dtype = torch.bfloat16
device = "cuda" if torch.cuda.is_available() else "cpu"
# Initialize CLIP tokenizer for prompt length checking
tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-base-patch32")
pipe = DiffusionPipeline.from_pretrained(
"UnfilteredAI/NSFW-Flux-v1",
torch_dtype=dtype
).to(device)
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 2048
MAX_TOKENS = 77 # CLIP's maximum token length
def truncate_prompt(prompt):
"""Truncate the prompt to fit within CLIP's token limit"""
tokens = tokenizer.encode(prompt, truncation=True, max_length=MAX_TOKENS)
return tokenizer.decode(tokens)
@spaces.GPU()
def infer(
prompt,
seed=42,
randomize_seed=False,
width=1024,
height=1024,
num_inference_steps=4,
progress=gr.Progress(track_tqdm=True)
):
# Truncate prompt if necessary
truncated_prompt = truncate_prompt(prompt)
if randomize_seed:
seed = random.randint(0, MAX_SEED)
generator = torch.Generator().manual_seed(seed)
try:
image = pipe(
prompt=truncated_prompt,
width=width,
height=height,
num_inference_steps=num_inference_steps,
generator=generator,
guidance_scale=0.0
).images[0]
return image, seed
except Exception as e:
raise gr.Error(f"Error generating image: {str(e)}")
examples = [
"a tiny astronaut hatching from an egg on the moon",
"a cat holding a sign that says hello world",
"an anime illustration of a wiener schnitzel",
]
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("""
NSFW-Flux-v1 is a 12 billion parameter rectified flow transformer
capable of generating images from text descriptions.
Finetuned by UnfilteredAI, this model is designed to produce
a wide range of images, including explicit and NSFW
(Not Safe For Work) images from textual inputs.
Note: Long prompts will be automatically truncated to fit the model's requirements.
""")
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)
with gr.Accordion("Advanced Settings", open=False):
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():
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=50,
step=1,
value=4,
)
gr.Examples(
examples=examples,
fn=infer,
inputs=[prompt],
outputs=[result, seed],
cache_examples="lazy"
)
gr.on(
triggers=[run_button.click, prompt.submit],
fn=infer,
inputs=[
prompt,
seed,
randomize_seed,
width,
height,
num_inference_steps
],
outputs=[result, seed]
)
demo.launch() |