---
title: DreamBooth-AltDiffusion
canonical_url: "https://www.modelscope.cn/models/BAAI/DreamBooth-AltDiffusion"
md_url: "https://www.modelscope.cn/models/BAAI/DreamBooth-AltDiffusion.md"
repository: BAAI/DreamBooth-AltDiffusion
last_updated: 2024-09-13
license: creativeml-openrail-m
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
library_name:
  - pytorch
  - lora
  - diffusers
frameworks:
  - pytorch
language:
  - zh
downloads: 2178
stars: 0
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - multilingual
  - "English(En)"
  - "Chinese(Zh)"
  - "Spanish(Es)"
  - "French(Fr)"
  - "Russian(Ru)"
  - "Japanese(Ja)"
  - "Korean(Ko)"
  - "Arabic(Ar)"
  - "Italian(It)"
  - diffusers
---

# DreamBooth-AltDiffusion

> DreamBooth-AltDiffusion - BAAI 在 ModelScope 开源的模型。This is a DreamBooth model finetuned from the multilingual text-to-image model AltDiffusion.

BAAI/DreamBooth-AltDiffusion 是 ModelScope 魔搭社区上的text-to-image-synthesis模型，采用 creativeml-openrail-m 许可。

- **Repository**: BAAI/DreamBooth-AltDiffusion
- **License**: creativeml-openrail-m
- **Tasks**: text-to-image-synthesis
- **Tags**: stable-diffusion, stable-diffusion-diffusers, text-to-image, multilingual, English(En), Chinese(Zh), Spanish(Es), French(Fr), Russian(Ru), Japanese(Ja), Korean(Ko), Arabic(Ar), Italian(It), diffusers
- **Downloads**: 2178
- **Stars**: 0
- **Last updated**: 2024-09-13

Source: https://www.modelscope.cn/models/BAAI/DreamBooth-AltDiffusion

---

# This is a DreamBooth model finetuned from the multilingual text-to-image model AltDiffusion.

Dreambooth is one of the method of finetune the pretrained text-to-image model.Given as input just a few images of a subject, it learns to bind a unique identifier with that specific subject.

AltDiffusion which is a multilingual text-to-image model.It currently supports 9 languages and will support more in future.
We can use the dreambooth to finetune the AltDiffusion,so that we can get a multilingual Dreambooth model which could supports 9 languages.

Here we give a example model finetuned use a dozen pictures of Uzumaki Naruto downloaded from web.The example code of inference is shown bellow.You can have a try and maybe train your own dreambooth.Hopes have fun!

## Example code of inference
```
from diffusers import AltDiffusionPipeline, DPMSolverMultistepScheduler
import torch

pipe = AltDiffusionPipeline.from_pretrained("BAAI/DreamBooth-AltDiffusion")
pipe = pipe.to("cuda")

pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)

prompt = "一张<鸣人>男孩的照片"
image = pipe(prompt, num_inference_steps=25).images[0]
image.show()
```