This repository implements DreamBooth subject fine-tuning for Stable Diffusion using textual inversion.
Open source
24 alternativesDreamBooth
DreamBooth describes fine-tuning text-to-image diffusion models to generate images of specific subjects.
About DreamBooth
DreamBooth describes a method for personalizing text-to-image diffusion models for subject-driven generation. Given a few images of a subject, it fine-tunes a pretrained model so a unique identifier is linked to that subject and can then be used in text prompts to generate the subject in different scenes.
The approach takes typically 3-5 images and the subject's class name, such as a specific dog and "dog". It fine-tunes the low-resolution model with a class-specific prior preservation loss and then fine-tunes the super-resolution components. Uses described include subject recontextualization, text-guided view synthesis, appearance modification, and artistic rendering while preserving the subject's key features.
Key features
- Fine-tunes text-to-image model using 3-5 images and class name
- Binds unique identifier to subject for use in prompts
- Generates subject in new scenes, poses, views, and lighting
- Produces text-guided view synthesis for specified viewpoints
- Creates artistic renditions of subject in painter styles
- Modifies subject appearance while preserving key features
Best for: Researchers and developers working with text-to-image diffusion models who need to generate a specific subject in new contexts from a few reference images.
Good for
- Works from typically 3-5 reference images per subject
- Preserves subject details while generating new contexts and interactions
- Generates poses, views, and lighting not present in reference images
DreamBooth at a glance
- Website
- dreambooth.github.io
- Type
- Website
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Open source
- Not stated
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
DreamBooth alternatives
Tools and sites you could use instead, ranked by how closely they match.
This repository includes examples and a guide for fine-tuning Stable Diffusion models.
Open source
24 alternatives
PyTorch Lightning extension that accelerates and enhances foundation model experimentation with flexible fine-tuning schedules.
Open source
24 alternatives
LightlyTrain supports pretraining, fine-tuning, and distillation for computer vision models.
Open source
24 alternatives
P-tuning v2 is a deep prompt tuning strategy designed as an alternative to full model fine-tuning.
Open source
24 alternatives
oumi supports fine-tuning, evaluation, and deployment of open-weight language models.
Open source
24 alternativesPopular in ML Training & Optimization
Well-known listings from the same topic.
Edwardedwardlib.orgAerosolveaerosolve.airbnb.techDataturedatature.ioTogether AItogether.aiOptunaoptuna.orgCatBoostcatboost.ai
DreamBooth FAQ
How many images of a subject are needed?
Typically 3-5 images suffice, based on the experiments described.
What inputs does the method require?
A few images of the subject and the corresponding class name, for example a specific dog and "dog".
Is the method limited to one text-to-image model?
It is demonstrated with Imagen, but the description states the method is not limited to a specific model.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.