KingHsp/vram-sage-training

Low VRAM SDXL Fine-Tuning Toolkit 2026: Train Full-Quality AI Models on 12GB GPUs

WeeLLM runs large diffusion models with as little as 4 GB of VRAM, without any quantization. It dynamically determines how many layers can fit within the available VRAM and streams the text encoder and transformer layers to the GPU layer by layer, enabling inference on hardware with limited VRAM. It supports both safetensors and GGUF models.

The ultimate training toolkit for finetuning diffusion models

Efficient Stable Diffusion Fine-Tuning Framework 2026: Lightweight Config-Driven Pipeline

Dead simple FLUX LoRA training UI with LOW VRAM support

Scalable and memory-optimized training of diffusion models

Memory Management for the GPU Poor, run the latest open source frontier models on consumer Nvidia GPUs

Low-VRAM LoRA Training for Krea-2

OneTrainer is a one-stop solution for all your Diffusion training needs.