Update app.py

app.py

@@ -1,154 +1,57 @@
 import gradio as gr
+import torch
 import numpy as np
 import random
-
-# import spaces #[uncomment to use ZeroGPU]
+import os
 from diffusers import DiffusionPipeline
-import torch
+import imageio
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
+torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
+# Load video model
+pipe = DiffusionPipeline.from_pretrained("stepfun-ai/stepvideo-t2v", torch_dtype=torch_dtype)
 pipe = pipe.to(device)
 
 MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
 
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
-def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
-):
+def infer(prompt, seed, randomize_seed, num_inference_steps):
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
+    generator = torch.manual_seed(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]
+    output = pipe(prompt=prompt, num_inference_steps=num_inference_steps, generator=generator)
+    frames = output.frames[0]  # list of PIL.Image
 
-    return image, seed
+    video_path = "/tmp/video.mp4"
+    imageio.mimsave(video_path, frames, fps=8)
 
+    return video_path, seed
 
 examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
+    "Astronaut dancing on Mars, cinematic lighting",
+    "A cat flying through the city on a skateboard",
+    "Robot chef cooking in a futuristic kitchen"
 ]
 
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 640px;
-}
-"""
-
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
-
-        with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-
-            run_button = gr.Button("Run", scale=0, variant="primary")
-
-        result = gr.Image(label="Result", show_label=False)
-
-        with gr.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+with gr.Blocks() as demo:
+    gr.Markdown("# Text-to-Video with `stepvideo-t2v`")
 
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
+    with gr.Row():
+        prompt = gr.Textbox(label="Prompt", placeholder="Enter your prompt here")
+        run_btn = gr.Button("Generate Video")
 
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
+    with gr.Row():
+        video_output = gr.Video(label="Generated Video")
 
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
-                )
+    with gr.Accordion("Advanced Settings", open=False):
+        seed = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0)
+        randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+        num_inference_steps = gr.Slider(label="Inference Steps", minimum=1, maximum=50, value=25)
 
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,  # Replace with defaults that work for your model
-                )
+    gr.Examples(examples=examples, inputs=[prompt])
 
-        gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
-    )
+    run_btn.click(fn=infer, inputs=[prompt, seed, randomize_seed, num_inference_steps], outputs=[video_output, seed])
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()