ComfyUI nodes for MiniT2I https://huggingface.co/MiniT2I/MiniT2I

Workflows are in the templates section.

Model	VRAM
b16	2.6GB
l16	4.3GB

Just a quickie. Bit slow cause the model is not cached in memory.

Changes

• v1.0.2: Split up into loader & inference nodes so ComfyUI handles VRAM, quicker.