Musubi Tuner adds VAE image support for MiniMax H3
bdsqlsz · x · 2026-08-15
The dev branch of Musubi Tuner now includes VAE image support and inference scripts for the MiniMax H3 model. Demonstrations show image editing capabilities via fl2va and ref2va models without additional training.
More from Multimodal
- Archviz creator wants to commission a ComfyUI workflow to AI-enhance 3D animation frames — PerfectoAllstar · 2026-08-15
- Converted 2D anime to 3D SBS video despite traditional depth sensor limitations — bdsqlsz · 2026-08-15
- Midjourney Prompting: Storytelling Through Object Still Life — tisch_eins · 2026-08-15
- Creator announces shift from 2D to exclusive dynamic 3D filming — TheTuringPost · 2026-08-15
- Test shows Qwen3.8-27b water surface rendering beats Gemini Flash — pbaylies · 2026-08-15
- Krea 2 Tiled Upscale Workflow for Detailed D&D Maps — 05032-MendicantBias · 2026-08-15