v0.9.1

What's Changed

• fix some bugs
• pkg: convert setup.py to standard pyproject.toml by @Borda in #208

Full Changelog: v0.9.0...v0.9.1

0.9.0

What's Changed

• Update README.md for MPS cases by @Atomic-Germ in #149
• Remove autocast for v2.1 by @seriousran in #144
• Add recursive option to upsample_imagefolder by @philgzl in #154
• Add utils and reuse functions in torch and flax pipelines by @charlielito in #157
• fix from_pretrained for models >= v2 by @nateraw in #166
• Add better logging by @philgzl in #156
• Add make_video as an option to StableDiffusionWalkPipeline.walk by @philgzl in #155
• update examples by @nateraw in #191
• update readme by @nateraw in #192
• Fix broken colab by @nateraw in #207

New Contributors

• @Atomic-Germ made their first contribution in #149
• @seriousran made their first contribution in #144
• @philgzl made their first contribution in #154

Full Changelog: v0.8.1...v0.9.0

0.8.1

What's Changed

• 🔥 Flax Implementation for TPU support by @charlielito in #140
• update release for 0.8.1 by @nateraw in #148

New Contributors

• 🔥 @charlielito made their first contribution in #140

Full Changelog: v0.8.0...v0.8.1

0.8.0

What's Changed

• Remove autocast from pipeline by @nateraw in #135

Full Changelog: v0.7.1...v0.8.0

0.7.1

What's Changed

• Hotfix 0.7.1 by @nateraw in #123

Full Changelog: v0.7.0...v0.7.1

0.7.0

What's Changed

• Update README.md by @thehappydinoa in #88
• Allow MPS devices to use the gradio interface by @ggozad in #105
• Fix typo in stable_diffusion_videos.ipynb by @eltociear in #115
• Diffusers 0.9.0 by @nateraw in #121

New Contributors

• @thehappydinoa made their first contribution in #88
• @ggozad made their first contribution in #105
• @eltociear made their first contribution in #115

Full Changelog: v0.6.2...v0.7.0

0.6.2

What's Changed

• Fix audio interpolation weight calculation by @nateraw in #95
• Add some example scripts by @nateraw in #96
• pin version to 0.6.2 by @nateraw in #97

Full Changelog: v0.6.1...v0.6.2

0.6.1

This release just pins av<10.0.0 as the latest version breaks torchvision.io.write_video, which we use in this package.

What's Changed

• Update requirements.txt by @nateraw in #91

Full Changelog: v0.6.0...v0.6.1

0.6.0

New Interface!

The interface is now a wrapper of the pipeline, which lets you use any pipeline instance you'd like in the app.

from stable_diffusion_videos import StableDiffusionWalkPipeline, Interface
import torch

pipeline = StableDiffusionWalkPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
    torch_dtype=torch.float16,
    revision="fp16",
).to("cuda")

interface = Interface(pipeline)
interface.launch(debug=True)

What's Changed

• ✨ add name to img generation, tiled attr to pipe by @nateraw in #78
• Updates for diffusers 0.5.1 by @nateraw in #82
• Cleanup and fix tests by @nateraw in #84
• New interface by @nateraw in #85
• Update notebook with new interface + access msg by @nateraw in #86
• Updates for diffusers 0.6.0 and release 0.6.0 by @nateraw in #87

Full Changelog: v0.5.3...v0.6.0

0.5.3

What's Changed

• Couple quick bugfixes by @nateraw in #74
• Fix audio alignment and add basic tests by @nateraw in #76
• Release 0.5.3 by @nateraw in #77

Full Changelog: v0.5.2...v0.5.3