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

Fix a couple typos in Dreambooth readme (#2004)

Browse Source 
Fix a couple typos in Dreambooth readme.
This commit is contained in:
Pedro Cuenca
2023-01-16 11:38:07 +01:00
committed by GitHub
parent 216d190178
commit 8f58159159
1 changed files with 3 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/dreambooth/README.md
View File

@@ -204,10 +204,9 @@ accelerate launch train_dreambooth.py \
--max_train_steps=800
```
### Using DreamBooth for other pipelines than Stable Diffusion
### Using DreamBooth for pipelines other than Stable Diffusion
Altdiffusion also support dreambooth now, the runing comman is basically the same as abouve, all you need to do is replace the `MODEL_NAME` like this:
One can now simply change the `pretrained_model_name_or_path` to another architecture such as [`AltDiffusion`](https://huggingface.co/docs/diffusers/api/pipelines/alt_diffusion).
The [AltDiffusion pipeline](https://huggingface.co/docs/diffusers/api/pipelines/alt_diffusion) also supports dreambooth fine-tuning. The process is the same as above, all you need to do is replace the `MODEL_NAME` like this:
```
export MODEL_NAME="CompVis/stable-diffusion-v1-4" --> export MODEL_NAME="BAAI/AltDiffusion-m9"
@@ -217,7 +216,7 @@ export MODEL_NAME="CompVis/stable-diffusion-v1-4" --> export MODEL_NAME="BAAI/Al
### Inference
Once you have trained a model using above command, the inference can be done simply using the `StableDiffusionPipeline`. Make sure to include the `identifier`(e.g. sks in above example) in your prompt.
Once you have trained a model using the above command, you can run inference simply using the `StableDiffusionPipeline`. Make sure to include the `identifier` (e.g. sks in above example) in your prompt.
```python
from diffusers import StableDiffusionPipeline