lllyasviel/ControlNet

Training still OOM on 8GB gpu.

Open

#21 aberto em 12 de fev. de 2023

Ver no GitHub
 (2 comments) (3 reactions) (0 assignees)Python (2.500 forks)batch import
help wanted

Métricas do repositório

Stars
 (27.526 stars)
Métricas de merge de PR
 (Nenhuma PRs mesclada em 30d)

Description

It seems that I already used many tricks but training still OOM for 8GB gpu. But inference is good now.

This is strange because I know some textural inversion or dreambooth can be trained on 8GB.

What is the secrect of Automatic1111's optimization? Although xformers may help a bit, the currect sliced attention should require even smaller mem than xformers.

Does it make sence to move text encoder and vae outside gpu when training?

Guia do colaborador