From 8f581591598255eff72cce8858f365eace47481f Mon Sep 17 00:00:00 2001 From: Pedro Cuenca Date: Mon, 16 Jan 2023 11:38:07 +0100 Subject: [PATCH] Fix a couple typos in Dreambooth readme (#2004) Fix a couple typos in Dreambooth readme. --- examples/dreambooth/README.md | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/examples/dreambooth/README.md b/examples/dreambooth/README.md index 93e6f4d14b..28ac0b4f6a 100644 --- a/examples/dreambooth/README.md +++ b/examples/dreambooth/README.md @@ -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