Potat 1️⃣
First Open-Source 1024x576 Text To Video Model 🥳
Info
Prototype Model
Trained with https://lambdalabs.com ❤ 1xA100 (40GB)
2197 clips, 68388 tagged frames ( salesforce/blip2-opt-6.7b-coco )
train_steps: 10000
Dataset & Config
https://huggingface.co/camenduru/potat1_dataset/tree/main
Finetuning
https://github.com/Breakthrough/PySceneDetect
https://github.com/ExponentialML/Video-BLIP2-Preprocessor
https://github.com/ExponentialML/Text-To-Video-Finetuning
https://github.com/camenduru/Text-To-Video-Finetuning-colab
Base Model
https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis
https://www.modelscope.cn/models/damo/text-to-video-synthesis
Thanks to damo-vilab ❤ ExponentialML ❤ kabachuha ❤ @DiffusersLib ❤ @LambdaAPI ❤ @cerspense ❤ @CiaraRowles1 ❤ @p1atdev_art ❤
Please try it 🐣
https://github.com/camenduru/text-to-video-synthesis-colab
Potat 2️⃣ is in the oven ♨