ComfyUI ecosystem updates — open-source model releases, custom nodes, workflows, and tools for image, video, and audio generation.
Image to videoAlibaba's TaoLive AIGC team released TaoMate-H3-FL2VA, a 3-step LoRA that adds first/last-frame control to streaming MiniMax H3 generation, with day-one ComfyUI conversions.
minimax-h3-community-license-agreement
Text to videoA rank-32 LoRA for MiniMax H3 continuation clips cuts face burn from +44% to 0% on lightx2v 8-step chains, and from +61% to +4% on an unseen turbo.
Text to speechComfyUI-Drama3 is a node pack that runs Fish Audio Drama 3 inside ComfyUI from 8 GB of VRAM, with voice cloning, 16-speaker dialogue, inline cues and Qwen3-ASR.
Image editingKokon is an open source desktop editor that runs Qwen-Image 2.1 Turbo locally through stable-diffusion.cpp: one installer, painted edits, AI upscaling and a built-in MCP server.
Text to imageFizgig v8 rebuilds the LoRA and fine-tune studio as a web app: train from a browser or your phone, borrow another computer's GPU, and open RunPod pods in the same window.
Text to videoSimplified Matching Distillation is a regression-only recipe for few-step diffusion. Its students cover FLUX, Qwen-Image, Wan2.1, MiniMax H3 and 3D, with ComfyUI workflows for H3.
Video editingAlissonerdx's MiniMax H3 LoRA pack adds a v1.0 character swap that recasts a guide clip's subject plus live wallpaper adapters, with ComfyUI workflows and examples.
BFS-Character-Swap-Community-1.1
EcosystemComfy-Org's Nvidia VFX Nodes reach 0.2.1 with RTX Video Super Resolution, RTX Video HDR and RTX Video Frame Generation, an official template and Manager install.
Image to imageFluxSR publishes its one-step 4x real-world super-resolution LoRA for Flux.1-dev, with training and inference code plus a ready community ComfyUI node pack.
FLUX-1-dev-non-commercial
Text to speechFish Audio releases Drama 3, a 35B MoE text-to-speech model that follows bracketed performance direction, with open weights and a ComfyUI partner node.
Fish Audio Community License 1.0
Text to imageLightX2V publishes a 4-step DMD-distilled Lightning LoRA for Qwen-Image 2.1, covering text-to-image and multi-reference editing with side-by-side samples.
Apache-2.0
EcosystemModelTC releases LightVAE, compressed Wan2.1, Wan2.2 and MiniMax-H3 video VAE decoders that keep the original latent interface, up to 2.94x faster in ComfyUI.
Apache-2.0
Text to videoSpark-H3 brings Spark-Attn block sparse attention to MiniMax-H3 in ComfyUI, with prebuilt nodes for RTX 40 and 50 series and a 1.73x faster DiT at 10% density.
Apache-2.0
EcosystemHEISS UI is an open-source local front end for ComfyUI: a prompt box and gallery over 28 model families, with missing files one click away and no node graph to wire.
MIT
Text to imageAlibaba's official Qwen-Image-2.1-Turbo checkpoint runs the 7B generator and editor in 8 denoising steps at CFG 1, with Comfy-Org repackaged weights for ComfyUI.
Qwen Research License
Video editingAkatz Labs' Person Remover LoRA tracks a person with SAM 3.1, fills the mask green and rebuilds the background in overlapping windows, with a ready ComfyUI workflow.
MiniMax H3 Community License
Image to imageA community LoRA for Qwen-Image 2.1 keeps a restored or enlarged photo on its original frame: 0.3 px off against 2.2 px without it, plus a ComfyUI workflow and two checkpoints.
Image editingakhaliq's Next-Scene LoRA teaches Qwen-Image 2.1 to render the next directed shot from a single frame, and to chain into storyboards through a ComfyUI LoRA node.
Apache-2.0
Image editingAkhaliq's Multiple-Angles LoRA gives Qwen-Image 2.1 camera control: feed a photo, pick one of 72 azimuth and elevation framings, and reshoot the subject in ComfyUI.
Apache-2.0
Text to imageLodestones ships Kroma v0.3.1 OPD for Krea 2: an on-policy distilled turbo checkpoint that stays inside the base model's distribution, with LoRA training carried over.