facebookresearch/fairseq

Support videoclip with newer version of dependencies

Open

#5,404 建立於 2023年12月19日

在 GitHub 查看
 (1 留言) (0 反應) (0 負責人)Python (29,107 star) (6,224 fork)batch import
enhancementhelp wantedneeds triage

描述

🚀 Feature Request

I hope there could be a code base for videoclip with newer version of dependencies (such as python, pytorch, transformers, diffusers, etc)

Motivation

Recently I am working on a project trying to combine videoclip with diffusion model, but found the denpendencies for videoclip (MMPT) in this repository confilict with modern diffusion models, As the modern diffusion models require newer version of diffusers, transformers and other dependencies.

Pitch

Would you please provide support for videoclip models with newer version of dependencies such as diffusers, transformers, tokenizers, etc?

貢獻者指南

技術棧
pythonpytorch
領域
machine learning
議題類型
feature
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
3
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
1-2 days
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
fresh
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
mostly clear
前置要求
PythonPyTorchDependency management
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
60
研究方向
Review the fairseq repository to locate the videoclip (MMPT) code, likely under fairseq/models or examples. Identify current dependency versions in setup.py or requirements.txt, then update the required packages (diffusers, transformers, tokenizers). Check the existing issue comments for more context and test integration with modern diffusion models.