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

small readme changes for advanced training examples (#10473)

Browse Source 
add to readme about hf login and wandb installation to address https://github.com/huggingface/diffusers/issues/10142#issuecomment-2571655570

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
This commit is contained in:
Linoy Tsaban
2025-01-10 03:05:19 +01:00
committed by GitHub
parent 7116fd24e5
commit 83ba01a38d
2 changed files with 22 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
examples/advanced_diffusion_training/README.md
View File

@@ -67,6 +67,17 @@ write_basic_config()
When running `accelerate config`, if we specify torch compile mode to True there can be dramatic speedups.
Note also that we use PEFT library as backend for LoRA training, make sure to have `peft>=0.6.0` installed in your environment.
Lastly, we recommend logging into your HF account so that your trained LoRA is automatically uploaded to the hub:
```bash
huggingface-cli login
```
This command will prompt you for a token. Copy-paste yours from your [settings/tokens](https://huggingface.co/settings/tokens),and press Enter.
> [!NOTE]
> In the examples below we use `wandb` to document the training runs. To do the same, make sure to install `wandb`:
> `pip install wandb`
> Alternatively, you can use other tools / train without reporting by modifying the flag `--report_to="wandb"`.
### Pivotal Tuning
**Training with text encoder(s)**

11
examples/advanced_diffusion_training/README_flux.md
View File

@@ -65,6 +65,17 @@ write_basic_config()
When running `accelerate config`, if we specify torch compile mode to True there can be dramatic speedups.
Note also that we use PEFT library as backend for LoRA training, make sure to have `peft>=0.6.0` installed in your environment.
Lastly, we recommend logging into your HF account so that your trained LoRA is automatically uploaded to the hub:
```bash
huggingface-cli login
```
This command will prompt you for a token. Copy-paste yours from your [settings/tokens](https://huggingface.co/settings/tokens),and press Enter.
> [!NOTE]
> In the examples below we use `wandb` to document the training runs. To do the same, make sure to install `wandb`:
> `pip install wandb`
> Alternatively, you can use other tools / train without reporting by modifying the flag `--report_to="wandb"`.
### Target Modules
When LoRA was first adapted from language models to diffusion models, it was applied to the cross-attention layers in the Unet that relate the image representations with the prompts that describe them.
More recently, SOTA text-to-image diffusion models replaced the Unet with a diffusion Transformer(DiT). With this change, we may also want to explore