Local Ai
None of this was us. Day 1 (and the first 48 hours) belonged to the open-source community: Generate with it @ComfyUI — native support + offi…
None of this was us. Day 1 (and the first 48 hours) belonged to the open-source community: Generate with it @ComfyUI — native support + official quantized builds, Day 0 Diffusers — the reference Pytho
None of this was us. Day 1 (and the first 48 hours) belonged to the open-source community: Generate with it @ComfyUI — native support + official quantized builds, Day 0 Diffusers — the reference Python pipeline, Day 0 @deepbeepmeep — WanGP v12.41, the 5-6 GB ultra-low VRAM path, Day 1 @pipenetwork — Phosphene + MiniMax-H3-MLX (one-click Mac app + MLX engine), Day 1 @blizaine — Maestro v1.5.5 (one-click GUI + prompt enhancer), Day 2 @ModelScope2022 — DiffSynth-Studio NF4, drops floor to 7-8 GB, Day 2 Serve it @sgl_project — SGLang Diffusion, official cookbook (2×5090 / RTX 6000), Day 0 @vllm_project — vLLM-Omni, OpenAI-compatible video endpoint, Day 0 Train it @ostrisai — AI Toolkit, first trainer (T2V + I2V) 14 h after release, Day 1 @ModelScope2022 — DiffSynth-Studio training scripts (NF4 low-memory), Day 2 @kohya_tech — Musubi Tuner, third trainer (48 GB → shrinking), Day 2 the first community LoRAs running on pruned INT8, Day 2 Speed it up @nvidia SANA team — Sol Engine, 3.95× end-to-end, no quality trade-off, Day 1 sol-attn · sage-attn · EasyCache — 20-35 % each on consumer cards (and they stack), Day 1 Spectrum acceleration — ~34 % Euler sampling time in ComfyUI, Day 2 @AMD — Day 0 support on Instinct MI300X / MI355X (ROCm + SGLang) Extend what it can do Multishot workflow — chains past the 15 s limit up to 30 s with audio, Day 2 Or just run it without installing @MiniMax_AI offical API @fal · @OpenRouter · official API — hosted from launch, 0.13/s for 2K, Day 0 @wavespeed_ai · @runpod — 0.07-0.15 per clip on rented 5090s, Day 2 And everyone who benchmarked, quantized (rockerBOO NVFP4, joeygambino GGUF…), and shared numbers: @umiyuki_ai @luta_ai @onigirikila @ivanfioravanti @Spectromachina and many more 🤗 This is what open weights are for. We just dropped SOTA open weights for our MiniMax‑H3 video model, and so much happened in 48 hours. The community ran H3 on untested hardware ($280 gaming GPUs, fully‑offline MacBooks) and built brand‑new unplanned tooling. Extremely glad we open‑sourced the weights. Community cr…
Source: ComfyUI (X) | 2026-08-05