Spaces:
Running
Running
| import gradio as gr | |
| import numpy as np | |
| import random | |
| from diffusers import DiffusionPipeline | |
| import torch | |
| # Set the device based on availability | |
| device = "cuda" if torch.cuda.is_available() else "cpu" | |
| # Use the ByteDance/AnimateDiff-Lightning model | |
| model_repo_id = "ByteDance/AnimateDiff-Lightning" | |
| # Set the torch dtype based on available hardware | |
| if torch.cuda.is_available(): | |
| torch_dtype = torch.float16 | |
| else: | |
| torch_dtype = torch.float32 | |
| # Load the pipeline from the pretrained model repository | |
| pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype) | |
| pipe = pipe.to(device) | |
| # Maximum values for seed and image size | |
| MAX_SEED = np.iinfo(np.int32).max | |
| MAX_IMAGE_SIZE = 1024 | |
| # Define the inference function | |
| def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, progress=gr.Progress(track_tqdm=True)): | |
| # Randomize seed if the checkbox is selected | |
| if randomize_seed: | |
| seed = random.randint(0, MAX_SEED) | |
| generator = torch.Generator(device=device).manual_seed(seed) | |
| # Generate the animation using the pipeline | |
| animation = 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] # Assuming the model generates images in the `.images` property | |
| return animation, seed | |
| # Sample prompts for the UI | |
| examples = [ | |
| "A cat playing with a ball in a garden", | |
| "A dancing astronaut in space", | |
| "A flying dragon in the sky at sunset", | |
| ] | |
| # Define CSS for styling | |
| css = """ | |
| #col-container { | |
| margin: 0 auto; | |
| max-width: 640px; | |
| } | |
| """ | |
| # Build the Gradio UI | |
| with gr.Blocks(css=css) as demo: | |
| with gr.Column(elem_id="col-container"): | |
| gr.Markdown(f""" | |
| # AnimateDiff Lightning Model Text-to-Animation | |
| """) | |
| 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) | |
| result = gr.Image(label="Generated Animation", 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=True, | |
| ) | |
| 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.Row(): | |
| width = gr.Slider( | |
| label="Width", | |
| minimum=256, | |
| maximum=MAX_IMAGE_SIZE, | |
| step=32, | |
| value=1024, | |
| ) | |
| height = gr.Slider( | |
| label="Height", | |
| minimum=256, | |
| maximum=MAX_IMAGE_SIZE, | |
| step=32, | |
| value=1024, | |
| ) | |
| with gr.Row(): | |
| guidance_scale = gr.Slider( | |
| label="Guidance scale", | |
| minimum=0.0, | |
| maximum=10.0, | |
| step=0.1, | |
| value=7.5, | |
| ) | |
| num_inference_steps = gr.Slider( | |
| label="Number of inference steps", | |
| minimum=1, | |
| maximum=50, | |
| step=1, | |
| value=30, | |
| ) | |
| # Example prompts for user selection | |
| gr.Examples( | |
| examples=examples, | |
| inputs=[prompt] | |
| ) | |
| # Create an API endpoint for the model | |
| demo.api(fn=infer, inputs=[prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps], outputs=[result, seed]) | |
| demo.launch() | |