User trains Krea2 LoRA on RTX 5070 Ti

The LoRA was trained on a dataset of 63 images using OneTrainer, achieving a speed of approximately 2.5 seconds per iteration. The full training process took between 2.5 and 3 hours at a 1024 resolution with a timestep shift of 2.5.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Cogent AI releases VR-1 cyber reasoning model
- Orchestrator tool integrates 12 AI coding agents in Visual Studio Code
- Taste Skill rules file for AI coding agents crosses 70,000 GitHub stars
- Hugging Face Diffusers flaws allow arbitrary code execution
- 139 Agent Skills bring legal workflows to Claude, Codex and Gemini CLI