character-consistency

Create high-fidelity Codex companions from 2+ photos with local open-weight neural editing and no OpenAI API key.

剧本分镜智能体（PenShot）：电影/动漫/短剧/小说→分镜片段→视频提示词。基于 LLM 通过 LangGraph+LlamaIndex实现任意格式剧本的自动解析���生成 Sora/Veo/Runway 等模型可用的连贯text-to-video提示词。保持角色/剧情跨片段一致，支持 MCP/REST API/Function Calls/A2A 集成。（LLM-powered text-to-video-prompt agent. Break scripts into Sora/Veo-ready shots with character consistency）

Build a person once, then shoot a whole series: framing, pose, placement, expression and aspect ratio vary while the person stays the same. ComfyUI nodes.

🎬 Turn any topic into a finished Zack D Films-style 3D animated short — curiosity-loop script, character sheets, 3D keyframes, Veo 3.1 motion, voiceover, captions & punchy edits, all automated. An agent skill for Claude Code, Codex & other coding agents. Powered by MuAPI + ffmpeg.

MiniMax H3 全域提示词工程 Skill v1.7｜AIMixer Director 导演台生产规则｜T2VA / I2VA / FL2VA / L2VA / Ref2VA｜Subject 与 Picture 语义分离、跨镜头因果桥、人物一致性、视频编辑、动作参考、音频控制、Prompt 修复｜ComfyUI / RunningHub / Codex

A local‑first AI pipeline that generates coherent images, videos, stories, dialogues, and spatial audio from an augmented storyboard. It structures prompts, ensures narrative continuity, automates sound spatialization, and provides a reproducible workflow for fast, high‑quality multimedia creation.

AI manga page generation skill pack with persistent character image memory for consistent characters across pages.

Python wrapper for Veo 4 API by Google DeepMind — native 4K AI video with integrated audio, character consistency & advanced camera controls.

AI-powered Claude skills for style-consistent image & video generation — keep characters, objects, and worlds on-model across every generation, no LoRA training required.

Turn any idea or article into hand-drawn editorial illustrations starring your own character — free on your ChatGPT/Codex sub. An agent skill (Claude Code, Codex, Cursor, Gemini) + a macOS app.

Local-first novel-to-comic generator — free, no GPU, pluggable providers.

End-to-end AI video creation pipeline: Script → Storyboard → Characters → Video with consistent character identity

Research implementation of a Recurrent-Depth Transformer for narrative reasoning, character consistency, and long-form story coherence.

Google Flow Prompt Guide: Veo Character Consistency, Storyboarding and Continuity

Codex + Doubao workflow for generating GPT Image-style magazine portraits from multi-angle character photos.

镜造 Image Forge — Codex Skill for reference-image distillation, character consistency and AI image generation: preserve hair, expression, pose, body, wardrobe and cinematography.

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.

AI Drama Video Creation Platform: End-to-End System | AI漫剧视频创作平台：端到端系统

AI Illustrator is a powerful tool designed to automatically generate consistent, high-quality illustrations for stories using Google's Gemini models for both text analysis and image generation.

Documentation and knowledge hub for Hailuo 3.0, MiniMax's next-gen 4K AI video model succeeding Hailuo 2.3.