ExponentialML/Text-To-Video-Finetuning

Finetune ModelScope's Text To Video model using Diffusers 🧨

Archived
41
/ 100
Emerging

Supports training full models or parameter-efficient LoRA adapters compatible with Stable Diffusion webui extensions. Implements memory optimizations including gradient checkpointing and Torch 2.0's Scaled Dot-Product Attention, enabling training on GPUs with ≤16GB VRAM. Provides flexible data preprocessing with automatic video captioning support and YAML-based configuration for customizing training on custom video datasets.

697 stars. No commits in the last 6 months.

Archived Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 22 / 25

How are scores calculated?

Stars

697

Forks

111

Language

Python

License

MIT

Last pushed

Dec 14, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ExponentialML/Text-To-Video-Finetuning"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.