0.5.2

Release 0.5.1 failed because I didn't update the version in init.py properly. retrying.

What's Changed

• 📌 update version to 0.5.1 by @nateraw in #72
• 📌 update release version to 0.5.2 by @nateraw in #73

Full Changelog: v0.5.1...v0.5.2

0.5.1

What's Changed

• Bugfixes by @nateraw in #69
• add image generation function by @nateraw in #70

Full Changelog: v0.5.0...v0.5.1

v0.5.0

What's Changed

🔥 This PR introduced ability to make music videos that interpolate to the beat of the song!!

• 🎨 big restructure by @nateraw in #65

Full Changelog: v0.4.0...v0.5.0

0.4.0

What's Changed

• CD: allow from draft by @Borda in #51
• use lerp for text by default by @nateraw in #55
• added param typing to walk function and updated the walk function to take in num_steps as a list by @danielpatrickhug in #52
• Rename num_steps to num_interpolation_steps by @nateraw in #61
• Update version to 0.4.0 by @nateraw in #62

New Contributors

• @Borda made their first contribution in #51
• @danielpatrickhug made their first contribution in #52

Full Changelog: v0.3.0...v0.4.0

0.3.0

stable_diffusion_videos==0.3.0 🚀

Highlights

Resume Support 🔥

You can now resume unfinished runs instead of starting over. Just pass resume=True and we'll resume the run at <output_dir>/<name>.

from stable_diffusion_videos import walk

video_path = walk(
    output_dir='dreams',
    name='my_unfinished_run',
    resume=True  # All you need to do!
)

Thank you to @codefaux for adding this feature.

Batch Inference 🔥

We've been generating frames one at a time. It's a lot faster to do more than one instead. Play with the batch_size kwarg until you go out of memory, then reduce the value by 1. For me, I am able to do batch_size=4 on a V100 16GB, which generates images ~20% faster.

from stable_diffusion_videos import walk

walk(
    prompts=['a cat', 'a dog'],
    seeds=[42, 123],
    batch_size=4,  # All you need to do!
    num_steps=60,
    make_video=True
)

What's Changed

• adding fps as param to walk by @kennethgoodman in #23
• Add option for lower VRAM by @0x1355 in #31
• Resume support by @codefaux and @nateraw in #42
• Remove unnecessary video file from repo by @nateraw in #43
• Add batch inference by @nateraw in #45
• Save in .png instead of .jpg by @0x1355 in #44
• Add frame_filename_ext to control saving/resuming from .png or .jpg by @nateraw in #47

New Contributors

• @kennethgoodman made their first contribution in #23
• @0x1355 made their first contribution in #31

Full Changelog: v0.2.0...v0.3.0

0.2.0

You can now do 4x upsampling (thanks to Real-ESRGAN) to make your results even more awesome!

What's Changed

• Add upsampling with Real-ESRGAN by @nateraw in #21
• 📌 update version by @nateraw in #22

Full Changelog: v0.1.2...v0.2.0

v0.1.2

What's Changed

• Add prompt config, various utils and update to diffusers==0.3.0 by @nateraw in #17
• Update version tag for 0.1.2 by @nateraw in #18

Full Changelog: v0.1.1...v0.1.2

0.1.1

Try release again

0.1.0

add pypi package