Update app.py

app.py

@@ -1,70 +1,120 @@
+import os
+import random
+import uuid
+
 import gradio as gr
 import numpy as np
-import random
-from diffusers import DiffusionPipeline
+from PIL import Image
+import spaces
 import torch
+from diffusers import (
+    StableDiffusionXLPipeline, 
+    KDPM2AncestralDiscreteScheduler,
+    AutoencoderKL
+)
+DESCRIPTION = """
+# Mobius
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
+a diffusion model that pushes the boundaries of domain-agnostic debiasing and representation realignment. By employing a brand new constructive deconstruction framework, Mobius achieves unrivaled generalization across a vast array of styles and domains, eliminating the need for expensive pretraining from scratch.
 
-if torch.cuda.is_available():
-    torch.cuda.max_memory_allocated(device=device)
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
-    pipe.enable_xformers_memory_efficient_attention()
-    pipe = pipe.to(device)
-else: 
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", use_safetensors=True)
-    pipe = pipe.to(device)
+Model by [Corcel.io](https://huggingface.co/Corcelio/mobius)
+"""
+if not torch.cuda.is_available():
+    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo may not work on CPU.</p>"
 
 MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
 
-def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
+USE_TORCH_COMPILE = 0
+ENABLE_CPU_OFFLOAD = 0
+
+device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+
+
+vae = AutoencoderKL.from_pretrained(
+    "madebyollin/sdxl-vae-fp16-fix", 
+    torch_dtype=torch.float16
+)
+
+# Configure the pipeline
+pipe = StableDiffusionXLPipeline.from_pretrained(
+    "Corcelio/openvision", 
+    vae=vae,
+    torch_dtype=torch.float16,
+)
+pipe.scheduler = KDPM2AncestralDiscreteScheduler.from_config(pipe.scheduler.config)
+pipe.to('cuda')
+
+def save_image(img):
+    unique_name = str(uuid.uuid4()) + ".png"
+    img.save(unique_name)
+    return unique_name
+
 
+def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
-        
-    generator = torch.Generator().manual_seed(seed)
-    
-    image = pipe(
-        prompt = prompt, 
-        negative_prompt = negative_prompt,
-        guidance_scale = guidance_scale, 
-        num_inference_steps = num_inference_steps, 
-        width = width, 
-        height = height,
-        generator = generator
-    ).images[0] 
+    return seed
+
+
+@spaces.GPU(enable_queue=True)
+def generate(
+    prompt: str,
+    negative_prompt: str = "",
+    use_negative_prompt: bool = False,
+    seed: int = 0,
+    width: int = 1280,
+    height: int = 1280,
+    guidance_scale: float = 1.5,
+    randomize_seed: bool = False,
+    progress=gr.Progress(track_tqdm=True),
+):
     
-    return image
+    pipe.to(device)
+    seed = int(randomize_seed_fn(seed, randomize_seed))
+
+    if not use_negative_prompt:
+        negative_prompt = ""  # type: ignore
+    images = pipe(
+        prompt=f'''{prompt}''',
+        negative_prompt=f"{negative_prompt}",     
+        width=width,
+        height=height,
+        guidance_scale=guidance_scale,
+        num_inference_steps=30,
+        num_images_per_prompt=1,
+        output_type="pil",
+    ).images
+
+    image_paths = [save_image(img) for img in images]
+    print(image_paths)
+    return image_paths, seed
+
+        
+
 
 examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
+    "a cat wearing sunglasses in the summer",
+    "an astronaut riding a horse on the moon",
+    "anime boy, protagonist,",
+    "A tiny robot taking a break under a tree in the garden",
 ]
 
-css="""
-#col-container {
-    margin: 0 auto;
-    max-width: 520px;
+css = '''
+.gradio-container{max-width: 560px !important}
+h1{text-align:center}
+footer {
+    visibility: hidden
 }
-"""
-
-if torch.cuda.is_available():
-    power_device = "GPU"
-else:
-    power_device = "CPU"
-
-with gr.Blocks(css=css) as demo:
-    
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(f"""
-        # Text-to-Image Gradio Template
-        Currently running on {power_device}.
-        """)
-        
+'''
+with gr.Blocks(title="Mobius", css=css) as demo:
+    gr.Markdown(DESCRIPTION)
+    gr.DuplicateButton(
+        value="Duplicate Space for private use",
+        elem_id="duplicate-button",
+        visible=False,
+    )
+    with gr.Group():
         with gr.Row():
-            
             prompt = gr.Text(
                 label="Prompt",
                 show_label=False,
@@ -72,75 +122,88 @@ with gr.Blocks(css=css) as demo:
                 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):
-            
+        result = gr.Gallery(label="Result", columns=1, preview=True, show_label=False)
+    with gr.Accordion("Advanced options", open=False):
+        with gr.Row():
+            use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=True)
             negative_prompt = gr.Text(
                 label="Negative prompt",
-                max_lines=1,
+                max_lines=6,
+                lines=4,
+                value="(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, (NSFW:0.25)",
                 placeholder="Enter a negative prompt",
-                visible=False,
-            )
-            
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
+                visible=True,
             )
-            
-            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=512,
-                )
-                
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=512,
-                )
-            
-            with gr.Row():
-                
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,
-                )
-                
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=12,
-                    step=1,
-                    value=2,
-                )
-        
-        gr.Examples(
-            examples = examples,
-            inputs = [prompt]
+        seed = gr.Slider(
+            label="Seed",
+            minimum=0,
+            maximum=MAX_SEED,
+            step=1,
+            value=0,
+            visible=True
         )
+        randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+        with gr.Row(visible=True):
+            width = gr.Slider(
+                label="Width",
+                minimum=512,
+                maximum=2048,
+                step=8,
+                value=1024,
+            )
+            height = gr.Slider(
+                label="Height",
+                minimum=512,
+                maximum=2048,
+                step=8,
+                value=1024,
+            )
+        with gr.Row():
+            guidance_scale = gr.Slider(
+                label="Guidance Scale",
+                minimum=0.1,
+                maximum=20,
+                step=0.1,
+                value=7.0,
+            )
 
-    run_button.click(
-        fn = infer,
-        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
-        outputs = [result]
+    gr.Examples(
+        examples=examples,
+        inputs=prompt,
+        outputs=[result, seed],
+        fn=generate,
+        cache_examples=False,
     )
 
-demo.queue().launch()
+    use_negative_prompt.change(
+        fn=lambda x: gr.update(visible=x),
+        inputs=use_negative_prompt,
+        outputs=negative_prompt,
+        api_name=False,
+    )
+    
+
+    gr.on(
+        triggers=[
+            prompt.submit,
+            negative_prompt.submit,
+            run_button.click,
+        ],
+        fn=generate,
+        inputs=[
+            prompt,
+            negative_prompt,
+            use_negative_prompt,
+            seed,
+            width,
+            height,
+            guidance_scale,
+            randomize_seed,
+        ],
+        outputs=[result, seed],
+        api_name="run",
+    )
+    
+if __name__ == "__main__":
+    demo.queue(max_size=20).launch(show_api=False, debug=False)