EveryDream2
Fine-tuning tool for Stable Diffusion focused on training quality.
About
EveryDream2 is a Stable Diffusion fine-tuning trainer focused on training on real captioned image sets rather than the token-and-class approach of DreamBooth. It supports SD 1.x and SDXL with aspect-ratio bucketing, captioning helpers, and detailed control over learning rate and schedules. It runs on Windows, Linux, or in Docker. Released under the MIT license and developed as a community project.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Model Training & Fine-Tuning
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- MIT
- Minimum VRAM
- 8 GB
- Added
- Apr 3, 2026
Related Tools
No-code tool by Hugging Face for training ML models automatically.
Efficient LLM quantization preserving important weight channels.
Video model fine-tuning toolkit by Hugging Face Diffusers team.
Low-code framework for building custom AI models by Predibase.
Library for training LLMs with reinforcement learning (RLHF, DPO, PPO).
Efficient fine-tuning method using 4-bit quantized base model with LoRA adapters.