Open Tylersuard opened 1 year ago
Hi, thanks for your interst in this repo.
You don't need to use Stable Diffusion images. You should be able to use the step 2 independently of step 1 and use a downscale factor of 2:
python generate_video.py --base_images_fullpath /path/to/image/folder --save_videos_fullpath /path/to/out/video --downscale_factor 2
When looking back at the code, their might be a bug when using other downscale factors than 4 so feel free to report back on your results
Hello, thank you for creating this repo. I prefer Midjourney to Stable Diffusion. I have 5 images that are 2x outpaintings. Would it be possible to use your code to make a zooming out video using my images?