| | --- |
| | license: mit |
| | --- |
| | |
| | # Text-to-Video Diffusion Model |
| |
|
| | This is a text-to-video diffusion model trained to generate video frames from text prompts. |
| |
|
| | ## Usage |
| |
|
| | ```python |
| | import torch |
| | from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler |
| | from diffusers.utils import export_to_video |
| | |
| | pipe = DiffusionPipeline.from_pretrained("your-username/text-to-video-diffusion", torch_dtype=torch.float16, variant="fp16") |
| | pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config) |
| | pipe.enable_model_cpu_offload() |
| | |
| | prompt = "Spiderman is surfing" |
| | video_frames = pipe(prompt, num_inference_steps=25).frames |
| | video_path = export_to_video(video_frames) |
| | |
