Minimax-h3_Singularity-x-10Eros-Max_PRISM
- 376
- 565k
- other
- 3 wk ago
ComfyUI node pack for HyperFlow [Video Rebirth's] 8-step LoRA for MiniMax-H3 (video + audio), ported onto ComfyUI's native MiniMax-H3 model. No ComfyUI core files are modified; no custom sampler is needed.
Image text to video model, used with diffusion-single-file.
MiniMax H3 全域提示词工程 Skill v1.8.1|AIMixer Director 导演台生产规则 + 武打/兵器/枪斗编排|T2VA / I2VA / FL2VA / L2VA / Ref2VA|Subject 与 Picture 语义分离、跨镜头因果桥、人物一致性、动作参考、音频控制、Prompt 修复|ComfyUI / RunningHub / Codex
5tar5ystem MMH3 Character Sheet Builder - a standalone ComfyUI pack that renders a MiniMax H3 character sheet from your references: reference roles, a matrix of views/poses/expressions, optional face blur, latent continuation between cells, frame picking and a composited sheet you can feed back into a ref2va workflow.
Image text to video model, used with diffusers.
MiniMax H3 多模态 LoRA 训练、审计与交付技能:Ref2VA、联合音视频、低显存后端与十步证据链。
Standalone MiniMax H3 Prompt & Conditioning Rig for ComfyUI
Image text to text model, used with gguf.
Image text to text model, used with gguf.
Story-to-MiniMax-H3 video prompt director skill: shot planning, segment packing, consistency assets, six-section Ref2VA prompts, and QA.