Update app.py

app.py

@@ -3,317 +3,102 @@ import torch
 import numpy as np
 import modin.pandas as pd
 from PIL import Image
-from diffusers import DiffusionPipeline, StableDiffusionLatentUpscalePipeline
+from diffusers import DiffusionPipeline
+from huggingface_hub import login
+import os
+from glob import glob
+from pathlib import Path
+from typing import Optional
+import uuid
+import random
 
+token = os.environ['HF_TOKEN']
+login(token=token)
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
-torch.cuda.max_memory_allocated(device=device)
-torch.cuda.empty_cache()
+pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-video-diffusion-img2vid-xt-1-1")
+#pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+pipe.enable_xformers_memory_efficient_attention()
+pipe = pipe.to(device)
+max_64_bit_int = 2**63 - 1
 
-def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, refine, high_noise_frac, upscale):
-    generator = np.random.seed(0) if seed == 0 else torch.manual_seed(seed)
-       
-    if Model == "PhotoReal":
-        pipe = DiffusionPipeline.from_pretrained("circulus/canvers-real-v3.8.1", torch_dtype=torch.float16, safety_checker=None) if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("circulus/canvers-real-v3.8.1")
-        pipe.enable_xformers_memory_efficient_attention()
-        pipe = pipe.to(device)
-        torch.cuda.empty_cache()
-        if refine == "Yes":
-            refiner = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", use_safetensors=True, torch_dtype=torch.float16, variant="fp16") if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0")
-            refiner.enable_xformers_memory_efficient_attention()
-            refiner = refiner.to(device)
-            torch.cuda.empty_cache()
-            int_image = pipe(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images
-            image = refiner(Prompt, negative_prompt=negative_prompt, image=int_image, denoising_start=high_noise_frac).images[0]
-            torch.cuda.empty_cache()
-            if upscale == "Yes":
-                refiner = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                refiner.enable_xformers_memory_efficient_attention()
-                refiner = refiner.to(device)
-                torch.cuda.empty_cache()
-                upscaled = refiner(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=15, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-                return image
-        else:
-            if upscale == "Yes":
-                image = pipe(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-                upscaler = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                upscaler.enable_xformers_memory_efficient_attention()
-                upscaler = upscaler.to(device)
-                torch.cuda.empty_cache()
-                upscaled = upscaler(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=15, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-               image = pipe(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-               torch.cuda.empty_cache()
-               return image
+def sample(
+    image: Image,
+    seed: Optional[int] = 42,
+    randomize_seed: bool = True,
+    motion_bucket_id: int = 127,
+    fps_id: int = 6,
+    version: str = "svd_xt",
+    cond_aug: float = 0.02,
+    decoding_t: int = 3,  # Number of frames decoded at a time! This eats most VRAM. Reduce if necessary.
+    device: str = "cpu",
+    output_folder: str = "outputs",):
+        
+    if image.mode == "RGBA":
+        image = image.convert("RGB")
+        
+    if(randomize_seed):
+        seed = random.randint(0, max_64_bit_int)
+    generator = torch.manual_seed(seed)
     
-    if Model == "Anime":
-        anime = DiffusionPipeline.from_pretrained("circulus/canvers-anime-v3.8.1", torch_dtype=torch.float16, safety_checker=None) if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("circulus/canvers-anime-v3.8.1")
-        anime.enable_xformers_memory_efficient_attention()
-        anime = anime.to(device)
-        torch.cuda.empty_cache()
-        if refine == "Yes":
-            refiner = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", use_safetensors=True, torch_dtype=torch.float16, variant="fp16") if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0")
-            refiner.enable_xformers_memory_efficient_attention()
-            refiner = refiner.to(device)
-            torch.cuda.empty_cache()
-            int_image = anime(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images
-            image = refiner(Prompt, negative_prompt=negative_prompt, image=int_image, denoising_start=high_noise_frac).images[0]
-            torch.cuda.empty_cache()
-            if upscale == "Yes":
-                refiner = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                refiner.enable_xformers_memory_efficient_attention()
-                refiner = refiner.to(device)
-                torch.cuda.empty_cache()
-                upscaled = refiner(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=15, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-                return image
-        else:
-            if upscale == "Yes":
-                image = anime(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-                upscaler = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                upscaler.enable_xformers_memory_efficient_attention()
-                upscaler = upscaler.to(device)
-                torch.cuda.empty_cache()
-                upscaled = upscaler(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=15, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-               image = anime(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-               torch.cuda.empty_cache()
-               return image
-                
-    if Model == "Disney":
-        disney = DiffusionPipeline.from_pretrained("circulus/canvers-disney-v3.8.1", torch_dtype=torch.float16, safety_checker=None) if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("circulus/canvers-disney-v3.8.1")
-        disney.enable_xformers_memory_efficient_attention()
-        disney = disney.to(device)
-        torch.cuda.empty_cache()
-        if refine == "Yes":
-            refiner = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", use_safetensors=True, torch_dtype=torch.float16, variant="fp16") if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0")
-            refiner.enable_xformers_memory_efficient_attention()
-            refiner = refiner.to(device)
-            torch.cuda.empty_cache()
-            int_image = disney(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images
-            image = refiner(Prompt, negative_prompt=negative_prompt, image=int_image, denoising_start=high_noise_frac).images[0]
-            torch.cuda.empty_cache()
-            
-            if upscale == "Yes":
-                refiner = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                refiner.enable_xformers_memory_efficient_attention()
-                refiner = refiner.to(device)
-                torch.cuda.empty_cache()
-                upscaled = refiner(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=15, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-                return image
-        else:
-            if upscale == "Yes":
-                image = disney(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-                upscaler = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                upscaler.enable_xformers_memory_efficient_attention()
-                upscaler = upscaler.to(device)
-                torch.cuda.empty_cache()
-                upscaled = upscaler(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=15, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else: 
-               image = disney(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-               torch.cuda.empty_cache()
-               return image
-            
-    if Model == "StoryBook":
-        story = DiffusionPipeline.from_pretrained("circulus/canvers-story-v3.8.1", torch_dtype=torch.float16, safety_checker=None) if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("circulus/canvers-story-v3.8.1")
-        story.enable_xformers_memory_efficient_attention()
-        story = story.to(device)
-        torch.cuda.empty_cache()
-        if refine == "Yes":
-            refiner = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", use_safetensors=True, torch_dtype=torch.float16, variant="fp16") if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0")
-            refiner.enable_xformers_memory_efficient_attention()
-            refiner = refiner.to(device)
-            torch.cuda.empty_cache()
-            int_image = story(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images
-            image = refiner(Prompt, negative_prompt=negative_prompt, image=int_image, denoising_start=high_noise_frac).images[0]
-            torch.cuda.empty_cache()
-            
-            if upscale == "Yes":
-                refiner = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                refiner.enable_xformers_memory_efficient_attention()
-                refiner = refiner.to(device)
-                torch.cuda.empty_cache()
-                upscaled = refiner(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=15, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-                return image
-        else:
-            if upscale == "Yes":
-                image = story(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-            
-                upscaler = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                upscaler.enable_xformers_memory_efficient_attention()
-                upscaler = upscaler.to(device)
-                torch.cuda.empty_cache()
-                upscaled = upscaler(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=15, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-                
-               image = story(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-               torch.cuda.empty_cache()
-               return image
+    os.makedirs(output_folder, exist_ok=True)
+    base_count = len(glob(os.path.join(output_folder, "*.mp4")))
+    video_path = os.path.join(output_folder, f"{base_count:06d}.mp4")
 
-    if Model == "SemiReal":
-        semi = DiffusionPipeline.from_pretrained("circulus/canvers-semi-v3.8.1", torch_dtype=torch.float16, safety_checker=None) if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("circulus/canvers-semi-v3.8.1")
-        semi.enable_xformers_memory_efficient_attention()
-        semi = semi.to(device)
-        torch.cuda.empty_cache()
-        if refine == "Yes":
-            refiner = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", use_safetensors=True, torch_dtype=torch.float16, variant="fp16") if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0")
-            refiner.enable_xformers_memory_efficient_attention()
-            refiner = refiner.to(device)
-            torch.cuda.empty_cache()
-            image = semi(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images
-            image = refiner(Prompt, negative_prompt=negative_prompt, image=image, denoising_start=high_noise_frac).images[0]
-            torch.cuda.empty_cache()
-            
-            if upscale == "Yes":
-                refiner = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                refiner.enable_xformers_memory_efficient_attention()
-                refiner = refiner.to(device)
-                torch.cuda.empty_cache()
-                upscaled = refiner(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=15, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-                return image
-        else:
-            if upscale == "Yes":
-                image = semi(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-            
-                upscaler = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                upscaler.enable_xformers_memory_efficient_attention()
-                upscaler = upscaler.to(device)
-                torch.cuda.empty_cache()
-                upscaled = upscaler(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=15, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-                
-                image = semi(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-                torch.cuda.empty_cache()
-                return image
+    frames = pipe(image, decode_chunk_size=decoding_t, generator=generator, motion_bucket_id=motion_bucket_id, noise_aug_strength=0.1, num_frames=25).frames[0]
+    export_to_video(frames, video_path, fps=fps_id)
+    torch.manual_seed(seed)
+    
+    return video_path, seed
 
-    if Model == "Animagine XL 3.0":
-        animagine = DiffusionPipeline.from_pretrained("cagliostrolab/animagine-xl-3.0", torch_dtype=torch.float16, safety_checker=None) if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("cagliostrolab/animagine-xl-3.0")
-        animagine.enable_xformers_memory_efficient_attention()
-        animagine = animagine.to(device)
-        torch.cuda.empty_cache()
-        if refine == "Yes":
-            torch.cuda.empty_cache()
-            torch.cuda.max_memory_allocated(device=device)
-            int_image = animagine(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale, output_type="latent").images
-            torch.cuda.empty_cache()
-            animagine = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", use_safetensors=True, torch_dtype=torch.float16, variant="fp16") if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0")
-            animagine.enable_xformers_memory_efficient_attention()
-            animagine = animagine.to(device)
-            torch.cuda.empty_cache()
-            image = animagine(Prompt, negative_prompt=negative_prompt, image=int_image, denoising_start=high_noise_frac).images[0]
-            torch.cuda.empty_cache()
-            
-            if upscale == "Yes":
-                animagine = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                animagine.enable_xformers_memory_efficient_attention()
-                animagine = animagine.to(device)
-                torch.cuda.empty_cache()
-                upscaled = animagine(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=15, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-                return image
-        else:
-            if upscale == "Yes":
-                image = animagine(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-            
-                upscaler = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                upscaler.enable_xformers_memory_efficient_attention()
-                upscaler = upscaler.to(device)
-                torch.cuda.empty_cache()
-                upscaled = upscaler(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=15, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-                
-               image = animagine(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-               torch.cuda.empty_cache()
-               return image
+def resize_image(image, output_size=(1024, 578)):
+    # Calculate aspect ratios
+    target_aspect = output_size[0] / output_size[1]  # Aspect ratio of the desired size
+    image_aspect = image.width / image.height  # Aspect ratio of the original image
 
-    if Model == "SDXL 1.0":
-        torch.cuda.empty_cache()
-        torch.cuda.max_memory_allocated(device=device)
-        sdxl = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
-        sdxl.enable_xformers_memory_efficient_attention()
-        sdxl = sdxl.to(device)   
-        torch.cuda.empty_cache()
-    
-        if refine == "Yes":
-            torch.cuda.max_memory_allocated(device=device)
-            torch.cuda.empty_cache()
-            image = sdxl(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale, output_type="latent").images
-            torch.cuda.empty_cache()
-            sdxl = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", use_safetensors=True, torch_dtype=torch.float16, variant="fp16") if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0")
-            sdxl.enable_xformers_memory_efficient_attention()
-            sdxl = sdxl.to(device)
-            torch.cuda.empty_cache()
-            refined = sdxl(Prompt, negative_prompt=negative_prompt, image=image, denoising_start=high_noise_frac).images[0]
-            torch.cuda.empty_cache()
-            
-            if upscale == "Yes":
-                sdxl = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                sdxl.enable_xformers_memory_efficient_attention()
-                sdxl = sdxl.to(device)
-                torch.cuda.empty_cache()
-                upscaled = sdxl(prompt=Prompt, negative_prompt=negative_prompt, image=refined, num_inference_steps=15, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-                return refined
-        else:
-            if upscale == "Yes":
-                image = sdxl(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-            
-                upscaler = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                upscaler.enable_xformers_memory_efficient_attention()
-                upscaler = upscaler.to(device)
-                torch.cuda.empty_cache()
-                upscaled = upscaler(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=15, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-                
-               image = sdxl(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-               torch.cuda.empty_cache()
-               
-            
-    return image
-    
-gr.Interface(fn=genie, inputs=[gr.Radio(['PhotoReal', 'Anime', 'Disney', 'StoryBook', 'SemiReal', 'Animagine XL 3.0', 'SDXL 1.0'], value='PhotoReal', label='Choose Model'),
-                               gr.Textbox(label='What you want the AI to generate. 77 Token Limit.'), 
-                               gr.Textbox(label='What you Do Not want the AI to generate. 77 Token Limit'),
-                               gr.Slider(512, 1024, 768, step=128, label='Height'),
-                               gr.Slider(512, 1024, 768, step=128, label='Width'),
-                               gr.Slider(1, maximum=15, value=5, step=.25, label='Guidance Scale'), 
-                               gr.Slider(25, maximum=100, value=50, step=25, label='Number of Iterations'), 
-                               gr.Slider(minimum=0, step=1, maximum=9999999999999999, randomize=True, label='Seed: 0 is Random'), 
-                               gr.Radio(["Yes", "No"], label='SDXL 1.0 Refiner: Use if the Image has too much Noise', value='No'),
-                               gr.Slider(minimum=.9, maximum=.99, value=.95, step=.01, label='Refiner Denoise Start %'),
-                               gr.Radio(["Yes", "No"], label = 'SD X2 Latent Upscaler?', value="No")],
-             outputs=gr.Image(label='Generated Image'), 
-             title="Manju Dream Booth V1.7 with SDXL 1.0 Refiner and SD X2 Latent Upscaler - GPU", 
-             description="<br><br><b/>Warning: This Demo is capable of producing NSFW content.", 
-             article = "If You Enjoyed this Demo and would like to Donate, you can send any amount to any of these Wallets. <br><br>BTC: bc1qzdm9j73mj8ucwwtsjx4x4ylyfvr6kp7svzjn84 <br>BTC2: 3LWRoKYx6bCLnUrKEdnPo3FCSPQUSFDjFP <br>DOGE: DK6LRc4gfefdCTRk9xPD239N31jh9GjKez <br>SHIB (BEP20): 0xbE8f2f3B71DFEB84E5F7E3aae1909d60658aB891 <br>PayPal: https://www.paypal.me/ManjushriBodhisattva <br>ETH: 0xbE8f2f3B71DFEB84E5F7E3aae1909d60658aB891 <br><br>Code Monkey: <a href=\"https://huggingface.co/Manjushri\">Manjushri</a>").launch(debug=True, max_threads=80)
+    # Resize then crop if the original image is larger
+    if image_aspect > target_aspect:
+        # Resize the image to match the target height, maintaining aspect ratio
+        new_height = output_size[1]
+        new_width = int(new_height * image_aspect)
+        resized_image = image.resize((new_width, new_height), Image.LANCZOS)
+        # Calculate coordinates for cropping
+        left = (new_width - output_size[0]) / 2
+        top = 0
+        right = (new_width + output_size[0]) / 2
+        bottom = output_size[1]
+    else:
+        # Resize the image to match the target width, maintaining aspect ratio
+        new_width = output_size[0]
+        new_height = int(new_width / image_aspect)
+        resized_image = image.resize((new_width, new_height), Image.LANCZOS)
+        # Calculate coordinates for cropping
+        left = 0
+        top = (new_height - output_size[1]) / 2
+        right = output_size[0]
+        bottom = (new_height + output_size[1]) / 2
+
+    # Crop the image
+    cropped_image = resized_image.crop((left, top, right, bottom))
+    return cropped_image
+
+with gr.Blocks() as demo:
+  #gr.Markdown('''# Community demo for Stable Video Diffusion - Img2Vid - XT ([model](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt), [paper](https://stability.ai/research/stable-video-diffusion-scaling-latent-video-diffusion-models-to-large-datasets), [stability's ui waitlist](https://stability.ai/contact))
+#### Research release ([_non-commercial_](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt/blob/main/LICENSE)): generate `4s` vid from a single image at (`25 frames` at `6 fps`). this demo uses [🧨 diffusers for low VRAM and fast generation](https://huggingface.co/docs/diffusers/main/en/using-diffusers/svd).
+  #''')
+  with gr.Row():
+    with gr.Column():
+        image = gr.Image(label="Upload your image", type="pil")
+        generate_btn = gr.Button("Generate")
+    video = gr.Video()
+  with gr.Accordion("Advanced options", open=False):
+      seed = gr.Slider(label="Seed", value=42, randomize=True, minimum=0, maximum=max_64_bit_int, step=1)
+      randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+      motion_bucket_id = gr.Slider(label="Motion bucket id", info="Controls how much motion to add/remove from the image", value=127, minimum=1, maximum=255)
+      fps_id = gr.Slider(label="Frames per second", info="The length of your video in seconds will be 25/fps", value=6, minimum=5, maximum=30)
+      
+  image.upload(fn=resize_image, inputs=image, outputs=image, queue=False)
+  generate_btn.click(fn=sample, inputs=[image, seed, randomize_seed, motion_bucket_id, fps_id], outputs=[video, seed], api_name="video",)# inputs=image, outputs=[video, seed], fn=sample, cache_examples=True,)
+
+if __name__ == "__main__":
+    demo.queue(max_size=20, api_open=False)
+    demo.launch(share=True, show_api=False)