ComfyUI
Every SLOP TV News story about ComfyUI.
Open weights is becoming a license tier, priced by revenue
ComfyUI is paying $25,000 for open-source rebuilds of Higgsfield's apps while Nvidia, whose cards are the prizes, backs Higgsfield.
MiniMax H3 cuts sampling to 4 steps with two open releases
FastH3 Omni ships as an 8-step ComfyUI student; Taobao's PTD LoRAs reach 4 steps, and neither release has independent quality benchmarks.
ComfyUI adds VEED nodes to lip-sync a still photo
The three cloud nodes also re-sync a speaker's mouth in footage you already shot and cut a subject out with an alpha matte.
ComfyUI's NVIDIA VFX nodes upscale AI video 4x for free
Three nodes that upscale, interpolate and convert to HDR now run in a ComfyUI graph, and frame generation needs a 40-series card.
Shots fired: ComfyUI pays $25,000 to rebuild Higgsfield in the open
Comfy says Higgsfield promised to open-source its platform and never did, so it put up $25,000 with NVIDIA and RunPod underwriting the fight. The question underneath is the one worth asking: is Comfy all you need?
How to run MiniMax H3 on a single 12GB graphics card
ComfyUI's repackaged weights cut MiniMax H3 from 123.6GB to 42.5GB, but the local build leaves out the hosted 2K stage behind Hailuo's showreels.
How to run MiniMax H3 on an 8 GB graphics card
FlashML-org's FreeVideo runs an eight-step MiniMax H3 derivative on small cards by streaming weights between GPU, RAM and disk.
ComfyUI 0.38 adds a 480p draft render for Seedance 2.5
The release also adds identity-preserving video-to-video on Wan 2.1 and VACE models, a new quantization format, and removes the retired Sora nodes.
4 free upgrades for local AI video released this week
ComfyUI, a timeline editor, an inpainting sampler and a camera-angle LoRA all shipped in the last four days, and all of them are free.
Qwen-Image-2.1 makes transparent 2K images for research use only
The 7B model puts a real alpha channel and native 2K output in one checkpoint, while the license drops from Apache 2.0 to research-only terms.
How to Train Your Own LTX-2.5 LoRA on One GPU, Step by Step
Lightricks' open trainer turns your clips into a small adapter that teaches the 22B video model a style, a face or a camera move. Here is the whole run.
MiniMax H3 add-ons multiply as downloads hit 4.3 million a month
September brought Video Rebirth's 8-step HyperFlow speed-up, a keyboard-driven world model called H3-World, TaoMate-H3, RefMods and a faster ComfyUI decoder.
MiniMax H3's free license excludes the US, EU, UK and South Korea
The MiniMax H3 Community License is royalty-free and allows commercial work, but it carves out four territories, a $20 million revenue ceiling and a ban on training other models.