Model card: 16 GB / 22 GB GPUs (ComfyUI workflows at a 14 GiB cap, inference.py --low-vram)

Add ready-to-run ComfyUI workflows (4- and 8-step, 15 s, 24 GB GPU)

Move the ComfyUI-layout LoRAs into minimax_h3/ next to the Diffusers-layout ones; update the card

Model card: ComfyUI sampling with stock lcm + simple (equivalent to the DMAD nodes)

Model card: ComfyUI section

Model card: all released DMAD weights (MiniMax-H3, Wan2.1, SDXL, ImageNet-64) and per-family licenses

Model card: authors, demo video badge, citation

Model card: say where the inference code is and add the clone step

Model card: project page URL

Model card: link the arXiv paper

Model card: link the code repository

Model card: title, badges and teaser

Model card: shorten the license paragraph

Add the 4-step DMAD students of MiniMax-H3 (lora_critic, full_critic), model card, license and notice

initial commit