ComfyUI ecosystem updates — open-source model releases, custom nodes, workflows, and tools for image, video, and audio generation.
Text to speechBilibili IndexTeam releases IndexTTS-2.5: zero-shot voice cloning in Chinese, English, Japanese, Spanish and Arabic, with emotion and speed control.
Bilibili Model License
Text to videoUnsloth publishes MiniMax H3 GGUF quants from Q2_K (6.3 GB) to Q8_0 (20 GB) for FL2VA and Ref2VA plus Qwen3-VL text encoder GGUFs for ComfyUI and stablediffusion.cpp.
Text to imageiljung1106's new ComfyUI node brings Normalized Attention Guidance to Krea 2, restoring negative-prompt control on Turbo checkpoints that require CFG 1.0.
Text to videoDownload h3-realism-people-t2v-i2v-r2v.safetensors (125 MB) into ComfyUI/models/loras for photoreal people in T2V, I2V and R2V with the r34l1sm trigger word.
Install the official MiniMax H3 skills from GitHub: h3-prompt-writing for all five generation modes plus eight style-specific video generation skills with bilingual SKILL.md files.
antirez, creator of Redis, builds h3.c, a native Metal-based MiniMax-H3 inference engine for Apple Silicon with prompt-to-video/audio and Ref2VA references working end to end.
MIT
Text to videoA ComfyUI custom node replaces MiniMax H3's 15.7 GB Qwen3-VL-32B text encoder with a Qwen3-VL-4B plus a learned projection, cutting conditioning VRAM to 4.5 GB.
MIT
InpaintingLanPaint 2.0.0 adds MiniMax H3 support with a video and audio inpainting pipeline: paint per-frame masks and audio intervals in one editor, then inpaint both in a single pass.
Text to imageLodestones releases Kroma v0.2 as a full Krea 2 fine-tuned checkpoint instead of a LoRA, with base and turbo files plus community INT8 quants for ComfyUI.
MIT
Video editingH3 Motion Context v0.2.0 chains MiniMax H3 clips so motion and audio continue across cuts, adds reference mode support, and removes the visible seam at joins.
Text to videoDownload h3_clean_latent_upscaler_v1_mamad8.safetensors (56 MB): Mamad8's 2x latent upscaler for MiniMax H3 with two ComfyUI nodes, doubling spatial resolution before VAE decode.
Text to videoDownload minimax_h3_turbo_v4_step600_ema.safetensors, the MiniMax H3 Turbo LoRA v4: 2-step audio-video generation in ComfyUI with pruned checkpoint support.
Image editingDownload minimax_h3_t1_image_vae_step1597.safetensors (5.2 GB): Mamad8's experimental MiniMax H3 VAE decodes a single T=1 latent directly into an image, no custom node required.
Text to videoLightx2v's MiniMax-H3-Prompt-Rewriter-LoRA turns short prompts into structured H3 T2VA descriptions locally, with a ComfyUI node pack for the Qwen3.6-27B adapter.
Character animationWan-Animate-2 and Wan-Animate-2-Lite for ComfyUI: character animation from driving video, text-driven viewpoint control, native nodes, real-time Lite for avatars.
Apache-2.0
Image to videoLightx2v and ModelTC distill MiniMax H3 into a 4-step FL2V Turbo LoRA, cutting sampling from ~20 steps to 4 with a ComfyUI conversion and demo Spaces.
Text to videoDownload MiniMax H3 Turbo LoRA (minimax_h3_turbo_4step_ckpt500.safetensors): 4-step video with synchronized stereo audio in ComfyUI, plus pruned conversion and T2V/I2V workflows.
Apache-2.0
Text to videotsuremen's new ComfyUI node scouts multiple seeds through the first steps of the MiniMax H3 schedule, shows live previews on the node, and finishes only the seed you pick.
Text to videoDownload Kijai's experimental w4a8 MiniMax H3 weights for ComfyUI: minimax_h3_fl2va_pruned_w4a8_mixed.safetensors (12.5 GB FL2VA), Ref2VA variant and int8 convrot VAE.
minimax-h3-community-license-agreement
Text to videoSand.ai open-sources MAGI-2 Preview, a 114B-parameter MoE that turns text or images into 10-second videos with synchronized audio, activating only 6B parameters per token.
Apache-2.0