iicd/ddpo-pytorch
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Kevin Black 2023-07-04 01:21:46 -07:00 committed by GitHub
parent 26177ccf40
commit b14022ea92
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -1,6 +1,6 @@
# ddpo-pytorch
This is an implementation of [Denoising Diffusion Policy Optimization (DDPO)](https://rl-diffusion.github.io/) in PyTorch with support for [low-rank adaptation (LoRA)](https://huggingface.co/docs/diffusers/training/lora). Unlike our original research code (which you can find [here](https://github.com/jannerm/ddpo)), this implementation runs on GPUs, and if LoRA is enabled, requires less than 10GB of GPU memory to finetune a Stable Diffusion-sized model!
This is an implementation of [Denoising Diffusion Policy Optimization (DDPO)](https://rl-diffusion.github.io/) in PyTorch with support for [low-rank adaptation (LoRA)](https://huggingface.co/docs/diffusers/training/lora). Unlike our original research code (which you can find [here](https://github.com/jannerm/ddpo)), this implementation runs on GPUs, and if LoRA is enabled, requires less than 10GB of GPU memory to finetune Stable Diffusion!
![DDPO](teaser.jpg)
@ -42,4 +42,4 @@ The image at the top of this README was generated using LoRA! However, I used a
You can find the exact configs I used for the 4 experiments in `config/dgx.py`. For example, to run the aesthetic quality experiment:
```bash
accelerate launch scripts/train.py --config config/dgx.py:aesthetic
```
```