Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
Paper • 2212.11565 • Published • 3
Text-to-Image
Diffusers
TuneAVideoPipeline
stable-diffusion
stable-diffusion-diffusers
text-to-video
tune-a-video
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Tune-A-Video-library/a-man-is-surfing", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Tune-A-Video - a-man-is-surfing
Model description
- Base model: CompVis/stable-diffusion-v1-4
- Training prompt: A man is surfing
Samples
Test prompt: A panda is surfing
Related papers:
- Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
- Stable-Diffusion: High-Resolution Image Synthesis with Latent Diffusion Models
- Downloads last month
- 5
Model tree for Tune-A-Video-library/a-man-is-surfing
Base model
CompVis/stable-diffusion-v1-4