nateraw/stable-diffusion-videos
nateraw/stable-diffusion-videos has 4,710 GitHub stars and 445 forks. GitHot measured 0 stars in 24 hours, +2 in 7 days, and -2 in 15 days. Last checked 2026-11-19 12:46 UTC. Last push 2025-12-16.
측정된 스타 증가
- in 24h
- 0
- in 7 days
- +2
- in 15 days
- -2
- in 1 month
- 기록 수집 중
서로 겹치는 기간의 순증가량이며 일별 합계가 아닙니다. 측정값이 없으면 비워 둡니다. 스타는 관심도를 나타내며 품질을 보장하지 않습니다.
소개
잠재 공간을 탐색하고 텍스트 프롬프트 간에 변형을 적용해 Stable Diffusion으로 🔥 동영상을 만듭니다
머신러닝README.md
Originalstable-diffusion-videos
Example - morphing between "blueberry spaghetti" and "strawberry spaghetti"
Installation
pip install stable_diffusion_videos
Usage
Check out the examples folder for example scripts 👀
Making Videos
Note: For Apple M1 architecture, use torch.float32 instead, as torch.float16 is not available on MPS.
from stable_diffusion_videos import StableDiffusionWalkPipeline
import torch
pipeline = StableDiffusionWalkPipeline.from_pretrained(
"CompVis/stable-diffusion-v1-4",
torch_dtype=torch.float16,
).to("cuda")
video_path = pipeline.walk(
prompts=['a cat', 'a dog'],
seeds=[42, 1337],
num_interpolation_steps=3,
height=512, # use multiples of 64 if > 512. Multiples of 8 if < 512.
width=512, # use multiples of 64 if > 512. Multiples of 8 if < 512.
output_dir='dreams', # Where images/videos will be saved
name='animals_test', # Subdirectory of output_dir where images/videos will be saved
guidance_scale=8.5, # Higher adheres to prompt more, lower lets model take the wheel
num_inference_steps=50, # Number of diffusion steps per image generated. 50 is good default
)
Making Music Videos
New! Music can be added to the video by providing a path to an audio file. The audio will inform the rate of interpolation so the videos move to the beat 🎶
from stable_diffusion_videos import StableDiffusionWalkPipeline
import torch
pipeline = StableDiffusionWalkPipeline.from_pretrained(
"CompVis/stable-diffusion-v1-4",
torch_dtype=torch.float16,
).to("cuda")
# Seconds in the song.
audio_offsets = [146, 148] # [Start, end]
fps = 30 # Use lower values for testing (5 or 10), higher values for better quality (30 or 60)
# Convert seconds to frames
num_interpolation_steps = [(b-a) * fps for a, b in zip(audio_offsets, audio_offsets[1:])]
video_path = pipeline.walk(
prompts=['a cat', 'a dog'],
seeds=[42, 1337],
num_interpolation_steps=num_interpolation_steps,
audio_filepath='audio.mp3',
audio_start_sec=audio_offsets[0],
fps=fps,
height=512, # use multiples of 64 if > 512. Multiples of 8 if < 512.
width=512, # use multiples of 64 if > 512. Multiples of 8 if < 512.
output_dir='dreams', # Where images/videos will be saved
guidance_scale=7.5, # Higher adheres to prompt more, lower lets model take the wheel
num_inference_steps=50, # Number of diffusion steps per image generated. 50 is good default
)
Using the UI
from stable_diffusion_videos import StableDiffusionWalkPipeline, Interface
import torch
pipeline = StableDiffusionWalkPipeline.from_pretrained(
"CompVis/stable-diffusion-v1-4",
torch_dtype=torch.float16,
).to("cuda")
interface = Interface(pipeline)
interface.launch()
Credits
This work built off of a script shared by @karpathy. The script was modified to this gist, which was then updated/modified to this repo.
Contributing
You can file any issues/feature requests here
Enjoy 🤗