Upload folder using huggingface_hub

README.md

@@ -1,13 +1,13 @@
 ---
-title: Perturbed Attention Guidance Sdxl 2
-emoji: 🐢
-colorFrom: gray
-colorTo: red
+title: Perturbed-Attention Guidance SDXL
+emoji: 🌀
+colorFrom: pink
+colorTo: yellow
 sdk: gradio
-sdk_version: 6.19.0
-python_version: '3.12'
+sdk_version: 5.43.1
 app_file: app.py
 pinned: false
+license: mit
 ---
 
-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 +1,83 @@
+import gradio as gr
+import spaces 
+from diffusers import StableDiffusionXLPipeline
+import numpy as np
+import math
+import torch 
+import random
+
+from gradio_imageslider import ImageSlider
+
+theme = gr.themes.Base(
+    font=[gr.themes.GoogleFont('Libre Franklin'), gr.themes.GoogleFont('Public Sans'), 'system-ui', 'sans-serif'],
+)
+
+pipe = StableDiffusionXLPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    custom_pipeline="multimodalart/sdxl_perturbed_attention_guidance",
+    torch_dtype=torch.float16
+)
+
+device="cuda"
+pipe = pipe.to(device)
+
+@spaces.GPU
+def run(prompt, negative_prompt=None, guidance_scale=7.0, pag_scale=3.0, pag_layers=["mid"], randomize_seed=True, seed=42, lora=None, progress=gr.Progress(track_tqdm=True)):
+    prompt = prompt.strip()
+    negative_prompt = negative_prompt.strip() if negative_prompt and negative_prompt.strip() else None
+    print(f"Initial seed for prompt `{prompt}`", seed)
+    if(randomize_seed):
+        seed = random.randint(0, 9007199254740991)
+    
+    if not prompt and not negative_prompt:
+        guidance_scale = 0.0
+    pipe.unfuse_lora()
+    pipe.unload_lora_weights()
+    if lora:
+        pipe.load_lora_weights(lora)
+        pipe.fuse_lora(lora_scale=0.9)
+    print(f"Seed before sending to generator for prompt: `{prompt}`", seed)
+    generator = torch.Generator(device="cuda").manual_seed(seed)
+    image_pag = pipe(prompt, negative_prompt=negative_prompt, guidance_scale=guidance_scale, pag_scale=pag_scale, pag_applied_layers=pag_layers, generator=generator, num_inference_steps=25).images[0]    
+    
+    generator = torch.Generator(device="cuda").manual_seed(seed)
+    image_normal = pipe(prompt, negative_prompt=negative_prompt, guidance_scale=guidance_scale, generator=generator, num_inference_steps=25).images[0]
+    print(f"Seed at the end of generation for prompt: `{prompt}`", seed)
+    return (image_pag, image_normal), seed
+
+css = '''
+.gradio-container{
+max-width: 768px !important;
+margin: 0 auto;
+}
+'''
+
+with gr.Blocks(css=css, theme=theme) as demo:
+    gr.Markdown('''# Perturbed-Attention Guidance SDXL
+    SDXL 🧨 [diffusers implementation](https://huggingface.co/multimodalart/sdxl_perturbed_attention_guidance) of [Perturbed-Attenton Guidance](https://ku-cvlab.github.io/Perturbed-Attention-Guidance/)
+    ''')
+    with gr.Group():
+      with gr.Row():
+        prompt = gr.Textbox(show_label=False, scale=4, placeholder="Your prompt", info="Leave blank to test unconditional generation")
+        button = gr.Button("Generate", min_width=120)
+      output = ImageSlider(label="Left: PAG, Right: No PAG", interactive=False)
+      with gr.Accordion("Advanced Settings", open=False):
+        guidance_scale = gr.Number(label="CFG Guidance Scale", info="The guidance scale for CFG, ignored if no prompt is entered (unconditional generation)", value=7.0)
+        negative_prompt = gr.Textbox(label="Negative prompt", info="Is only applied for the CFG part, leave blank for unconditional generation")
+        pag_scale = gr.Number(label="Pag Scale", value=3.0)
+        pag_layers = gr.Dropdown(label="Model layers to apply Pag to", info="mid is the one used on the paper, up and down blocks seem unstable", choices=["up", "mid", "down"], multiselect=True, value="mid")
+        randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+        seed = gr.Slider(minimum=1, maximum=9007199254740991, step=1, randomize=True)
+        lora = gr.Textbox(label="Custom LoRA path", info="Load a custom LoRA from Hugging Face to use PAG with")
+    gr.Examples(fn=run, examples=[" ", "an insect robot preparing a delicious meal, anime style", "a photo of a group of friends at an amusement park"], inputs=prompt, outputs=[output, seed], cache_examples="lazy")
+    gr.on(
+        triggers=[
+            button.click,
+            prompt.submit
+        ],
+        fn=run,
+        inputs=[prompt, negative_prompt, guidance_scale, pag_scale, pag_layers, randomize_seed, seed, lora],
+        outputs=[output, seed],
+    )
+if __name__ == "__main__":
+    demo.launch(share=True)

requirements.txt

@@ -0,0 +1,6 @@
+diffusers
+transformers
+accelerate
+safetensors
+peft
+https://huggingface.co/spaces/multimodalart/face-to-all/resolve/main/gradio_imageslider-0.0.19-py3-none-any.whl?download=true