stable-diffusion-videos
stable-diffusion-videos copied to clipboard
nateraw
Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
The TPU Version wont start. ``` ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following...
Hi, Thank you for open-sourcing this great work. I am trying to execute a video format where I would like to interpolate from a black screen(image) to a certain prompt...
A cat  ACA
I executed this code on the mac of M1 ``` from stable_diffusion_videos import StableDiffusionWalkPipeline, Interface import torch pipeline = StableDiffusionWalkPipeline.from_pretrained( "CompVis/stable-diffusion-v1-4", torch_dtype=torch.float32, revision="fp16", ).to("mps") interface = Interface(pipeline) interface.launch() ``` and...
Is there no way to use one base seed and have it altered for each frame so it animates and doesnt just move to a completely new image for each...
Hey @nateraw, thatnks for providing your helpful repo to create videos! Me as an artist would love to have such a tool, but I'm not that familiar with python environments...
Closes #168 The solution was to ping the flax and diffussers version and avoid upgrading flax from colab already installed version
@nateraw Code: ``` from stable_diffusion_videos import StableDiffusionWalkPipeline import torch pipeline = StableDiffusionWalkPipeline.from_pretrained( "prompthero/openjourney-v4", torch_dtype=torch.float16, revision="fp16", ).to("cuda") video_path = pipeline.walk( prompts=['a cat', 'a dog'], seeds=[42, 1337], num_interpolation_steps=20, height=512, # use multiples...
Can somebody explain me: 1: How the seeds work? I've manage to make it work and I gave random seeds number. But I really would like to know what I...
Hello, I'm curious to find out about the minimum and recommended system resource requirements to run stable-diffusion-video model predictions. If there are any benchmarks or examples, that would be great!...
