Video, 3D, sound, and more

3D generation

GitHub - openai/point-e: Point cloud diffusion for 3D model synthesisGitHub

Point E - a Hugging Face Space by openaihuggingface

DreamFusion

https://dreamfusion3d.github.io/

Sound

RiffusionRiffusion

Video

Meta: https://makeavideo.studio/

Phenaki: https://phenaki.video/

GitHub - pschaldenbrand/Text2Video: A fast approach for translating a series of text prompts into a video. The 2022 NeurIPS Workshop on Machine Learning for Creativity and DesignGitHub

Video using stable diffusion

Making your first AI-generated animation with Deforum Stable DiffusionMedium

3D generation from few shots: NeRF

NeRF: Neural Radiance FieldsMedium

CLIP interrogation: from pictures to prompts

CLIP Interrogator - a Hugging Face Space by pharmahuggingface

Super Resolution

What is ‘Image Super Resolution’, and why do we need it?Medium