ExponentialML/Text-To-Video-Finetuning
Fine-tuning pipeline for ModelScope text-to-video diffusion models using the Diffusers library.
Not currently ranked — collecting fresh signals.
star history
This repository provides tools to fine-tune ModelScope text-to-video diffusion models with support for LoRA training, gradient checkpointing, and Torch 2.0 scaled dot product attention. It enables converting trained models from Diffusers format to .ckpt for use with A1111 webui, and includes compatibility with sd-webui-text2video extensions.
Frequently asked
- What is ExponentialML/Text-To-Video-Finetuning?
- Fine-tuning pipeline for ModelScope text-to-video diffusion models using the Diffusers library.
- Is Text-To-Video-Finetuning open source?
- Yes — ExponentialML/Text-To-Video-Finetuning is open source, released under the MIT license.
- What language is Text-To-Video-Finetuning written in?
- ExponentialML/Text-To-Video-Finetuning is primarily written in Python.
- How popular is Text-To-Video-Finetuning?
- ExponentialML/Text-To-Video-Finetuning has 699 stars on GitHub.
- Where can I find Text-To-Video-Finetuning?
- ExponentialML/Text-To-Video-Finetuning is on GitHub at https://github.com/ExponentialML/Text-To-Video-Finetuning.