pDMD LoRA brings 2-step realtime editing to MiniMax's 33B image model at 16MP
_akhaliq · x · 2026-11-11
akhaliq shipped a pDMD 2-NFE LoRA (arXiv 2609.35768, rank 128 over attention+FFN of all 50 blocks) merged into MiniMax-H3-Image's official 33.1B transformer, producing finished images in 2 denoising steps at native 4096×4096 with no CFG.
- Ships diffusers-layout LoRA, a ComfyUI native-layout conversion, and a one-file bf16 ComfyUI checkpoint with the LoRA pre-merged (no LoRA node needed)
- Runs realtime editing on ZeroGPU; demo and weights are public
Related event: Two-Step pDMD LoRA Speeds Up MiniMax H3-Image(2 posts)→
More from Multimodal
- Gemini 4 Carbon's Boeing 747 artifact goes live on HF Space with wireframe and lighting modes — victormustar · 2026-11-11
- The 'Boeing Bench': AI models race to build a Boeing 747, Fable 5.2 beats Gemini 4 Carbon — victormustar · 2026-11-11
- Same prompt face-off: FABLE 5.2 vs Gemini 4 Argon draw an illuminated-manuscript magpie — teortaxesTex · 2026-11-11
- Can you tell which is real? AI-edited conference photo goes viral for its realism — threepointone · 2026-11-11
- Turning household sounds into instruments with Gemini 4 (FFT + onset detection) — alexanderchen · 2026-11-11
- Midjourney dual-sref combo yields whimsical storybook fantasy art — Kyrannio · 2026-11-11