Try it yourself in Colab:
Example - morphing between "blueberry spaghetti" and "strawberry spaghetti"
berry_good_spaghetti.2.mp4
pip install stable_diffusion_videosCheck out the examples folder for example scripts 👀
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
)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
)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()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.
You can file any issues/feature requests here
Enjoy 🤗
