Text to imageBase model
Meta Muse Image Comes to ComfyUI as Official API NodesComfyUI adds two official Meta Muse Image API nodes: text-to-image and image edit with up to 10 input images, 14 aspect ratios, and a reasoning strength control.
ComfyUI News & Open-Source AI Releases
ComfyUI ecosystem updates — open-source model releases, custom nodes, workflows, and tools for image, video, and audio generation.
Text to image
Text to imageTool
Recraft V4 Styles and Styles Pro: Brand-Controlled Styling in ComfyUIComfyUI's Recraft nodes add V4 Styles and Styles Pro models to the Create Style node, pairing custom trained styles with a style reference workflow for consistent branding.
Image to videoLoRA
MiniMax H3 Turbo Ref2VA 8-Step v1.0: Reference-to-Video LoRADownload minimax_h3_ref2v_turbo_8step_v1.0_comfyui_bf16.safetensors: Lightx2v's 8-step 768p Ref2VA distillation for MiniMax H3 with audio, plus updated example workflows.
Text to imageTool
Krea2T Enhancer Adds Attention-Weighted Phrases for Krea 2capitan01R's Krea2T Enhancer adds an Attention-Weighted Phrases node for Krea 2: boost or suppress individual prompt phrases directly in the DiT attention.
Text to videoTool
ComfyUI-MiniMaxH3-CLIPCached: Disk Cache for H3 ConditioningA new ComfyUI node caches MiniMax H3 Qwen3-VL conditioning to disk: repeat runs with the same prompt skip the 14.6 GB encoder, dropping conditioning from 29.9 s to 1.1 s.
Text to videoBase model
DreamX-Creator 1.0: Open 7B Joint Audio-Video Generation at 2KAMap open-sources DreamX-Creator 1.0, a 7B joint audio-video generator with gated cross-modal attention and a 1-step 2K refiner, built on Wan2.2 and fully downloadable.
MultimodalTool
MiniMax Music Production Toolkit: Full Music Studio in ComfyUIA free MIT node pack turns ComfyUI into a MiniMax Music 3 production studio: LLM-written song prompts, 62 genre presets, FlashSR upscaling to 48 kHz and automatic FLUX.2 cover art.
Text to videoTurbo
MiniMax H3 Max and H3 Max Turbo Join ComfyUI Partner NodesComfyUI's MiniMax video nodes add H3 Max and H3 Max Turbo: a quality-focused and a speed-focused hosted variant supporting text-to-video, first-last-frame, and reference workflows.
Text to videoBase model
VDN-H3: Hybrid Attention Runs MiniMax H3 Video Faster Than PlaybackOpenVDN's Video DeltaNet hybrid attention checkpoint for MiniMax H3 renders a 14.4s 768p clip in 8 steps, with a community ComfyUI port already available.
minimax-h3-community-license-agreement
Text to imageTool
Expert Text Prompt: AST-Based Prompt Parser Node for ComfyUIA new ComfyUI custom node parses prompts as an AST: weighted wildcards, prompt groups, inline mute and solo, automatic negative routing and a built-in syntax checker.
Image to imageTool
Provcheck Adds a C2PA Watermark Node for ComfyUIProvcheck v1.4.0 brings an offline C2PA signing node to ComfyUI: neural watermarks for image and audio, plus Content Credentials bound to your Bluesky handle.
Image to videoTool
Endless MiniMax H3 v1.0: Unlimited-Length Lip-Synced H3 VideosA new workflow combines H3 Motion Context with a latent-saver node to chain MiniMax H3 clips into unlimited-length videos, with lip-sync, on a 12GB GPU.
Image to imageTool
VibeComfy x Hivemind: Agents That Read and Edit ComfyUI WorkflowsVibeComfy translates ComfyUI workflow JSON into editable Python for CLI agents, and now pairs with the Hivemind knowledge base for community-sourced workflow patterns.
Image editingTool
OpenGPEX: Browser Image Editor That Runs ComfyUI WorkflowsOpenGPEX is an open-source browser image editor that connects to your ComfyUI instance, runs any workflow and drops the result back as an editable layer.
Image to imageTool
ComfyUI-DLSS5-NR: DLSS 5 Neural Rendering Runs Inside ComfyUIAn experimental ComfyUI node runs NVIDIA DLSS 5 Neural Rendering in-process through a D3D12 bridge, enhancing images and video frames without leaving your workflow.
Text to videoTool
H3 Acceleration Arena: Blind-Test Ranking of MiniMax H3 SpeedupsA blind A/B arena from the ComfyUI community ranks 23 MiniMax H3 acceleration variants: FastH3, H3 Turbo distills, SLA, PDD and merges, voted on 4000 pre-generated clips.
Image to videoLoRA
H3-World: Keyboard-Controlled Interactive World Model on MiniMax H3H3-World turns MiniMax H3 into an interactive world model: a 65.6M LoRA plus an attention patch maps WASD and camera keys to action-controlled video from a single frame.
apache-2.0
Text to imageBase model
Diffusion Compiler Speeds Up Krea 2 Turbo on Consumer GPUsAn open source C++20 compiler for diffusion models runs Krea 2 Turbo prompt-to-PNG over 2x faster than ComfyUI on an RTX 3090 Ti, with MiniMax H3 in progress.
Video editingBase model
Viggle-Animate: H3 Character Replacement From a Single Repainted FrameViggle-Animate is a 33.1B finetune of MiniMax H3 ref2va with DMD distillation that swaps video characters from one repainted frame, 3 forward passes, 26 seconds per clip.
minimax-h3-community-license-agreement
Text to videoLoRA
vh5tape: Worn VHS Style LoRA for MiniMax H3 with Tape Audiovh5tape makes MiniMax H3 footage look like a worn 1980s VHS recording, with tracking noise, chroma bleed and matching tape-hiss audio. Three prompt-controlled damage levels.