Upload 3 files

README.md

@@ -1,13 +1,15 @@
 ---
-title: Test
-emoji: 💻
-colorFrom: pink
-colorTo: yellow
+title: test
+emoji: 👨‍🎨
+colorFrom: red
+colorTo: green
 sdk: gradio
 sdk_version: 4.42.0
 app_file: app.py
 pinned: false
-license: cc-by-nc-4.0
+suggested_hardware: t4-medium
+startup_duration_timeout: 1h
+disable_embedding: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,195 @@
+import torch
+import gradio as gr
+from PIL import Image
+import qrcode
+from pathlib import Path
+import requests
+import io
+import os
+import spaces
+import random
+
+from diffusers import (
+    StableDiffusionXLControlNetPipeline,
+    ControlNetModel,
+    AutoencoderKL,
+    DiffusionPipeline,
+    DDIMScheduler,
+    DPMSolverMultistepScheduler,
+    DEISMultistepScheduler,
+    HeunDiscreteScheduler,
+    EulerDiscreteScheduler,
+)
+
+MAX_SEED = 2**32 - 1
+
+# QR Code generation setup
+qrcode_generator = qrcode.QRCode(
+    version=1,
+    error_correction=qrcode.ERROR_CORRECT_H,
+    box_size=16,
+    border=4,
+)
+
+# SDXL and ControlNet setup
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
+
+controlnet = ControlNetModel.from_pretrained(
+    "AGCobra/1",
+    torch_dtype=torch.float16
+).to(device)
+
+pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    vae=vae,
+    controlnet=controlnet,
+    torch_dtype=torch.float16,
+    use_safetensors=True,
+    variant="fp16",
+).to(device)
+
+# Sampler setup
+SAMPLER_MAP = {
+    "DPM++ Karras SDE": lambda config: DPMSolverMultistepScheduler.from_config(config, use_karras=True, algorithm_type="sde-dpmsolver++"),
+    "DPM++ Karras": lambda config: DPMSolverMultistepScheduler.from_config(config, use_karras=True),
+    "Heun": lambda config: HeunDiscreteScheduler.from_config(config),
+    "Euler": lambda config: EulerDiscreteScheduler.from_config(config),
+    "DDIM": lambda config: DDIMScheduler.from_config(config),
+    "DEIS": lambda config: DEISMultistepScheduler.from_config(config),
+}
+
+def resize_for_condition_image(input_image: Image.Image, resolution: int):
+    input_image = input_image.convert("RGB")
+    W, H = input_image.size
+    k = float(resolution) / min(H, W)
+    H *= k
+    W *= k
+    H = int(round(H / 64.0)) * 64
+    W = int(round(W / 64.0)) * 64
+    img = input_image.resize((W, H), resample=Image.LANCZOS)
+    return img
+
+@spaces.GPU()
+def inference(
+    qr_code_content: str,
+    prompt: str,
+    negative_prompt: str,
+    guidance_scale: float = 7.5,
+    controlnet_conditioning_scale: float = 1.1,
+    strength: float = 0.9,
+    seed: int = -1,
+    sampler: str = "DPM++ Karras SDE",
+):
+    if prompt is None or prompt == "":
+        raise gr.Error("Prompt is required")
+
+    if qr_code_content == "":
+        raise gr.Error("QR Code Content is required")
+
+    pipe.scheduler = SAMPLER_MAP[sampler](pipe.scheduler.config)
+
+    if seed == -1:
+        seed = random.randint(0, MAX_SEED)
+    
+    # Use a sub-seed for additional randomness
+    subseed = random.randint(0, MAX_SEED)
+    generator = torch.Generator(device=device).manual_seed(seed + subseed)
+
+    print("Generating QR Code from content")
+    qr = qrcode.QRCode(
+        version=1,
+        error_correction=qrcode.constants.ERROR_CORRECT_H,
+        box_size=16,
+        border=4,
+    )
+    qr.add_data(qr_code_content)
+    qr.make(fit=True)
+
+    qrcode_image = qr.make_image(fill_color="black", back_color="white")
+    qrcode_image = resize_for_condition_image(qrcode_image, 1024)
+
+    init_image = qrcode_image
+
+    out = pipe(
+        prompt=prompt,
+        negative_prompt=negative_prompt,
+        image=init_image,
+        control_image=qrcode_image,
+        controlnet_conditioning_scale=float(controlnet_conditioning_scale),
+        guidance_scale=float(guidance_scale),
+        generator=generator,
+        strength=float(strength),
+        num_inference_steps=30,
+    )
+    return out.images[0]
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        with gr.Column():
+            qr_code_content = gr.Textbox(
+                label="QR Code Content",
+                info="QR Code Content or URL",
+                value="",
+            )
+
+            prompt = gr.Textbox(
+                label="Prompt",
+                info="Prompt that guides the generation towards",
+            )
+            negative_prompt = gr.Textbox(
+                label="Negative Prompt",
+                value="ugly, disfigured, low quality, blurry",
+            )
+
+            with gr.Accordion(
+                label="Advanced Parameters",
+                open=True,
+            ):
+                controlnet_conditioning_scale = gr.Slider(
+                    minimum=0.0,
+                    maximum=2.0,
+                    step=0.01,
+                    value=1.1,
+                    label="Controlnet Conditioning Scale",
+                )
+                strength = gr.Slider(
+                    minimum=0.0, maximum=1.0, step=0.01, value=0.9, label="Strength"
+                )
+                guidance_scale = gr.Slider(
+                    minimum=0.0,
+                    maximum=50.0,
+                    step=0.25,
+                    value=7.5,
+                    label="Guidance Scale",
+                )
+                sampler = gr.Dropdown(choices=list(SAMPLER_MAP.keys()), value="DPM++ Karras SDE", label="Sampler")
+                seed = gr.Slider(
+                    minimum=-1,
+                    maximum=MAX_SEED,
+                    step=1,
+                    value=-1,
+                    label="Seed",
+                    randomize=True,
+                )
+            with gr.Row():
+                run_btn = gr.Button("Run")
+        with gr.Column():
+            result_image = gr.Image(label="Result Image")
+    run_btn.click(
+        inference,
+        inputs=[
+            qr_code_content,
+            prompt,
+            negative_prompt,
+            guidance_scale,
+            controlnet_conditioning_scale,
+            strength,
+            seed,
+            sampler,
+        ],
+        outputs=[result_image],
+    )
+
+demo.queue(max_size=20).launch(share=bool(os.environ.get("SHARE", False)))

requirements.txt

@@ -0,0 +1,9 @@
+diffusers
+transformers
+accelerate
+torch
+xformers
+gradio
+Pillow
+qrcode
+gradio==4.8.0