YURIformer is a project where you can train LLMs more efficiently and with simplicity :D
-
Updated
Apr 29, 2026 - Python
YURIformer is a project where you can train LLMs more efficiently and with simplicity :D
Lightweight SDXL LoRA trainer optimized for 8GB VRAM GPUs. GUI with training, auto-captioning (Ollama) and image search (SearXNG).
From-scratch anime/manga AI — custom MoE architecture with specialized experts for line art, color theory, and background generation. Trains on 2,000+ images with full resource management (L3 cache, SSD offload, OOM prevention) on mid-range hardware. Single-file pipeline from dataset collection to inference.
Add a description, image, and links to the low-vram-training topic page so that developers can more easily learn about it.
To associate your repository with the low-vram-training topic, visit your repo's landing page and select "manage topics."