PODoptimizer / app.py
Jenaydd's picture
Create app.py
7438126 verified
Raw History Blame Contribute Delete
5.07 kB
import gradio as gr
from diffusers import StableDiffusionImg2ImgPipeline
import torch
from PIL import Image
import io
import random
# ---- STYLE PROMPTS ----
STYLE_PROMPTS = {
"no style change": "",
"tattoo": "blackwork tattoo style, bold clean lines, vector look, high contrast",
"street art": "street art mural style, graffiti, spray paint, bold outlines, urban, vector look",
"pop art": "pop art style, halftone dots, bold primary colors, clean outlines",
"minimalism": "minimalist vector illustration, simple flat colors, lots of negative space",
"geometric": "geometric vector art, sharp shapes, clean lines, abstract patterns",
"y2k": "Y2K digital art style, chrome, gradients, early 2000s web aesthetics, shiny, vector look",
"abstract": "abstract vector art, bold shapes, experimental, high contrast",
"trippy": "psychedelic trippy art, warped shapes, vivid colors, surreal, vector look",
"retro": "retro vintage poster style, muted colors, worn texture, clean outlines",
"grunge": "grunge poster art, distressed textures, rough edges, dark tones"
}
TARGET_MAX_SIDE = 6000 # pixels (good for shirts, posters, etc.)
DPI = 350
# ---- LOAD PIPELINE ----
MODEL_ID = "runwayml/stable-diffusion-v1-5"
device = "cuda" if torch.cuda.is_available() else "cpu"
pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
MODEL_ID,
torch_dtype=torch.float16 if device == "cuda" else torch.float32
).to(device)
def resize_for_model(image: Image.Image, max_side: int = 1024) -> Image.Image:
w, h = image.size
scale = max_side / max(w, h)
if scale < 1:
new_size = (int(w * scale), int(h * scale))
return image.resize(new_size, Image.LANCZOS)
return image
def upscale_to_target(image: Image.Image, target_max_side: int = TARGET_MAX_SIDE) -> Image.Image:
w, h = image.size
max_side = max(w, h)
if max_side >= target_max_side:
return image
scale = target_max_side / max_side
new_size = (int(w * scale), int(h * scale))
return image.resize(new_size, Image.LANCZOS)
def generate_pod_art(input_image, style_name, num_variants=3, strength=0.7, guidance_scale=7.5):
if input_image is None:
return []
base_image = input_image.convert("RGB")
# Prepare for model
model_input = resize_for_model(base_image, max_side=1024)
style_prompt = STYLE_PROMPTS.get(style_name, "")
if style_name == "no style change":
# Just try to keep content; no heavy style
prompt = "high resolution, clean, vector-style illustration, print-on-demand ready"
strength_val = 0.3 # stay close to original
else:
prompt = f"{style_prompt}, high resolution, vector-style illustration, print-on-demand ready"
strength_val = strength
outputs = []
for _ in range(num_variants):
seed = random.randint(0, 2**32 - 1)
generator = torch.Generator(device=device).manual_seed(seed)
if device == "cuda":
with torch.autocast(device):
result = pipe(
prompt=prompt,
image=model_input,
strength=strength_val,
guidance_scale=guidance_scale,
num_inference_steps=30,
generator=generator
)
else:
with torch.no_grad():
result = pipe(
prompt=prompt,
image=model_input,
strength=strength_val,
guidance_scale=guidance_scale,
num_inference_steps=30,
generator=generator
)
out_image = result.images[0]
# Upscale for POD
out_image = upscale_to_target(out_image, target_max_side=TARGET_MAX_SIDE)
# Set DPI metadata when saving to bytes
buf = io.BytesIO()
out_image.save(buf, format="PNG", dpi=(DPI, DPI))
buf.seek(0)
pil_out = Image.open(buf)
outputs.append(pil_out)
return outputs
def process(input_image, style):
images = generate_pod_art(input_image, style)
return images
with gr.Blocks() as demo:
gr.Markdown("# POD-Ready Art Generator\nUpload an image, pick a style, get 3 high-res 350 DPI PNGs for print-on-demand.")
with gr.Row():
with gr.Column():
input_img = gr.Image(label="Input Image", type="pil")
style_dropdown = gr.Dropdown(
label="Style",
choices=list(STYLE_PROMPTS.keys()),
value="no style change"
)
generate_btn = gr.Button("Generate POD Art")
with gr.Column():
gallery = gr.Gallery(
label="Generated Images",
show_label=True,
columns=3,
height=400,
preview=True
)
generate_btn.click(
fn=process,
inputs=[input_img, style_dropdown],
outputs=[gallery]
)
if __name__ == "__main__":
demo.launch()