refactor Lora LoraAdapter and the latent_diffusion/lora file

finegrain-ai · Jan 18, 2024 · a1f50f3 · a1f50f3
1 parent dd87b97
commit a1f50f3
Show file tree

Hide file tree

Showing 12 changed files with 427 additions and 871 deletions.
diff --git a/README.md b/README.md
@@ -158,16 +158,6 @@ You should get:
 
 ![dropy slime output](https://raw.githubusercontent.com/finegrain-ai/refiners/main/assets/dropy_slime_9752.png)
 
-### Training
-
-Refiners has a built-in training utils library and provides scripts that can be used as a starting point.
-
-E.g. to train a LoRA on top of Stable Diffusion, copy and edit `configs/finetune-lora.toml` to suit your needs and launch the training as follows:
-
-```bash
-python scripts/training/finetune-ldm-lora.py configs/finetune-lora.toml
-```
-
 ## Adapter Zoo
 
 For now, given [finegrain](https://finegrain.ai)'s mission, we are focusing on image edition tasks. We support:

diff --git a/configs/finetune-lora.toml b/configs/finetune-lora.toml
diff --git a/scripts/conversion/convert_diffusers_lora.py b/scripts/conversion/convert_diffusers_lora.py
diff --git a/scripts/conversion/convert_refiners_lora_to_sdwebui.py b/scripts/conversion/convert_refiners_lora_to_sdwebui.py