This repository includes examples and a guide for fine-tuning Stable Diffusion models.
Open source
24 alternativesJoePenna/Dreambooth-Stable-Diffusion
github.com/JoePenna/Dreambooth-Stable-Diffusion
ML Training & Optimization
Open-source projectOpen source
This repository implements DreamBooth subject fine-tuning for Stable Diffusion using textual inversion.
About JoePenna/Dreambooth-Stable-Diffusion
This open-source repository implements DreamBooth subject fine-tuning for Stable Diffusion using textual inversion. It includes tweaks focused on training faces, objects, and styles. The author describes the tool as designed for digital artists to train their own characters and styles, and for people to train their own likenesses, with a stated goal of helping filmmakers and concept artists generate initial visual ideas.
Training requires a GPU with 24GB of VRAM, such as a 3090, according to the source. Training will be slower, and no other program should be running. For users without that hardware, the repository includes Jupyter notebooks tailored to runpod.io and vast.ai, and it states support for a Google Colab notebook. The author strongly discourages training other people's art without explicit permission or a public statement about this technology, and recommends against using artists' names in prompts. The source also states that the implementation does not fully implement Google's ideas on preserving the latent space. Pricing is unknown.
Key features
- Fine-tunes Stable Diffusion using DreamBooth subject training combined with textual inversion
- Modifications intended for training faces, objects, and styles
- Jupyter notebooks for running training on runpod.io and vast.ai
- Google Colab notebook support
- Included scripts named merge_embeddings.py and prune_ckpt.py
- Setup guides for Vast.ai, Google Colab, and local Windows or Ubuntu PCs
Best for: Digital artists, filmmakers, concept artists, and comic book designers who have a 24GB VRAM GPU or access to rented cloud GPUs and want to train Stable Diffusion on specific characters, styles, or likenesses.
Good for
- Open source, with a LICENSE file included in the repository
- Cloud notebooks allow training without owning a 24GB VRAM GPU
- Includes multiple how-to guides for different setup environments
Watch out for
- Local use requires a GPU with 24GB of VRAM, and training is slower
- Notebooks are tailored to runpod.io and vast.ai
- Does not fully implement Google's ideas on preserving the latent space
JoePenna/Dreambooth-Stable-Diffusion at a glance
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
JoePenna/Dreambooth-Stable-Diffusion alternatives
Tools and sites you could use instead, ranked by how closely they match.
DreamBooth describes fine-tuning text-to-image diffusion models to generate images of specific subjects.
This repository implements random forest models in Common Lisp for classification tasks.
Open source
24 alternatives
PyTorch Lightning extension that accelerates and enhances foundation model experimentation with flexible fine-tuning schedules.
Open source
24 alternatives
This Common Lisp repository collects algorithms for online linear classification.
Open source
24 alternatives
This metric-learn repository contains Python implementations of metric learning algorithms.
Open source
24 alternativesPopular in ML Training & Optimization
Well-known listings from the same topic.
Edwardedwardlib.orgDataturedatature.ioAerosolveaerosolve.airbnb.techTogether AItogether.aiOptunaoptuna.orgCatBoostcatboost.ai
JoePenna/Dreambooth-Stable-Diffusion FAQ
What hardware is needed to run this locally?
The source states a GPU with 24GB of VRAM, such as a 3090. Training will be slower, and no other program should be running during training.
Can it be run without a local high-VRAM GPU?
The repository includes Jupyter notebooks for rented cloud platforms, tailored to runpod.io and vast.ai, and states support for a Google Colab notebook.
Is it appropriate to train the model on other people's artwork?
The author strongly discourages training someone else's art unless explicit permission has been obtained or the artist has made a public statement about this technology. The author also recommends against using artists' names in prompts.
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.