AI Agent 驱动的开源可自部署视频工作台:将小说与剧本转为角色、场景、道具资产、分镜、视频和剪映草稿,支持跨镜头一致性、多供应商与费用追踪 | Self-hosted AI video workspace for stories, storyboards and short-form video production
-
Updated
Nov 18, 2026 - Python
AI Agent 驱动的开源可自部署视频工作台:将小说与剧本转为角色、场景、道具资产、分镜、视频和剪映草稿,支持跨镜头一致性、多供应商与费用追踪 | Self-hosted AI video workspace for stories, storyboards and short-form video production
[ECCV 2026] Official PyTorch implementation of RefAlign: Representation Alignment for Reference-to-Video Generation
Direct MiniMax H3 like a pro: Idea in, finished video out. A complete MiniMax H3 studio that lives in your ComfyUI.
Premiere-inspired PySide6 director studio for MiniMax H3 Ref2VA with AI shot planning, semantic media enrichment, timeline prompt reconciliation and shot-aware long-video rendering through ComfyUI.
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
Self-hosted MiniMax H3 video with native audio and Qwen Image. Adaptive ComfyUI workflows, character references, storyboards and saved scenes.
Original MiniMax H3 prompt library, MuAPI Python client, API examples, and current model notes.
ComfyUI custom nodes for MiniMax H3 video prompt generation (T2V, I2V, R2V). Timeline, camera, characters, dialogue, audio and Korean translation.
ComfyUI node pack for MiniMax H3 — chains generations into one continuous clip with held identity
ComfyUI custom nodes for Veo 3.1 video generation — text-to-video, image-to-video, reference-to-video, extend, and 4K upscale via MuAPI
MiniMax H3 (Hailuo 3.0) front-end for ComfyUI — text-to-video, image-to-video, first-and-last-frame and reference-to-video with native audio. A local LLM writes H3's structured prompts and self-corrects them. Character consistency from a subject photo, live preview, VRAM handoff.
ComfyUI custom nodes for MiniMax H3 text-to-video, image-to-video, and multimodal reference-to-video generation through Muapi.
Uncensored Wan 3.0 API wrapper (Python): relaxed-moderation Alibaba video generator via MuAPI with synchronized audio and high motion.
Quality-first local MiniMax H3 video-series generation and loopback API for dual RTX 4090 workstations, with native audio, references, P8/P9 continuity, and preserved artifacts.
71 tested prompts for AI videos that keep the same person, pet or product in every shot — prompt, reference photos and result for Kling, Seedance, Wan and other reference-to-video models.
MiniMax H3 本地视频生成时间线工作台:编排多镜头提示词、参数与参考素材,支持文生视频、图生视频及多模态参考模式,并对接本地推理后端。 | A local MiniMax H3 video-generation timeline studio for multi-shot prompts, settings, and reference media, supporting text-to-video, image-to-video, and multimodal reference modes via a local inference backend.
Uncensored MiniMax H3 Spicy API examples: compare 8 relaxed-moderation H3, H3 Max and H3 Max Turbo video endpoints on MuAPI, with schemas, pricing, cURL, Python and JS.
ComfyUI MiniMax H3 workflows: T2V, I2V, Ref2V, variable duration and LM Studio prompts / 音声付き動画・可変尺・日本語入力
Pinned, hash-verified Comfy-Org MiniMax H3 ComfyUI workflows for T2V, I2V and R2V, with RTX 3060 benchmark evidence.
本地 MiniMax H3 参考生视频(R2V)竖屏玩龙工作流 —— ComfyUI,8GB 显存可跑,含 <Picture 1> 参考图绑定用法
To associate your repository with the reference-to-video topic, visit your repo's landing page and select "manage topics."