AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity

[research_projects] Update README.md to include a note about NF5 T5-xxl (#9775)

Browse Source 
Update README.md
This commit is contained in:
Sayak Paul
2024-10-26 22:13:03 +09:00
committed by GitHub
parent 298ab6eb01
commit fddbab7993
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
examples/research_projects/flux_lora_quantization/README.md
View File

@@ -5,7 +5,8 @@
This example shows how to fine-tune [Flux.1 Dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) with LoRA and quantization. We show this by using the [`Norod78/Yarn-art-style`](https://huggingface.co/datasets/Norod78/Yarn-art-style) dataset. Steps below summarize the workflow:
* We precompute the text embeddings in `compute_embeddings.py` and serialize them into a parquet file.
* We precompute the text embeddings in `compute_embeddings.py` and serialize them into a parquet file.
* Even though optional, we load the T5-xxl in NF4 to further reduce the memory foot-print.
* `train_dreambooth_lora_flux_miniature.py` takes care of training:
* Since we already precomputed the text embeddings, we don't load the text encoders.
* We load the VAE and use it to precompute the image latents and we then delete it.
@@ -163,4 +164,4 @@ image.save("yarn_merged.png")
|-------|-------|
| ![Image A](https://huggingface.co/datasets/sayakpaul/sample-datasets/resolve/main/quantized_flux_training/merged.png) | ![Image B](https://huggingface.co/datasets/sayakpaul/sample-datasets/resolve/main/quantized_flux_training/unmerged.png) |
As we can notice the first column result follows the style more closely.
As we can notice the first column result follows the style more closely.