generative-manim

English | 中文说明 | Español | Deutsch | 한국어

---

Generative Manim

🎨 GPT-4o powered generative videos. Concept. ⚡️ Join our Discord server here!

---

🚀 Concept

Generative Manim (GM) is a suite of tools that allows you to create videos with Manim using LLMs (Large Language Models) like GPT-4 or Claude. The idea is to enable anyone to create wonderful animations from text ✨.

It began as a prototype of a web app that uses GPT-4 to generate videos with Manim. The idea behind this project is taking advantage of the power of LLMs in programming, the understanding of human language and the animation capabilities of Manim to generate a tool that could be used by anyone to create videos. Regardless of their programming or video editing skills.

• 🖐️ Generative Manim Demo: Check out the demo of Generative Manim!
• 🔬 Generative Manim API: Build over the Animation Processing Interface, or API.
• ☁️ Cloud Deployment Guide: Deploy the API on Render or another Docker-based cloud platform.
• 🧑‍💻 Generative Manim Developers: Join our Discord server, learn new things, share your creations and more!
• 🍎 Generative Manim Streamlit (Legacy): First LLM exploration of LLMs and Animation.
• 🧩 Manim Awesome Skills: A curated collection of Manim skills and snippets.

🎬 Animo

Animo is a lightweight desktop application that turns plain English descriptions into animated videos using AI and Manim. It is the natural evolution of Generative Manim, taking everything built in this repository and packaging it into a polished, self-contained desktop experience.

Key improvements over Generative Manim:

• Desktop-first, local rendering: animations render on your machine with no cloud uploads, giving you full privacy and control over your work.
• Unified workflow: everything lives in one app with no need to juggle a web UI, a separate API, and a render environment.
• Zero extra cost: Animo uses your existing Claude or ChatGPT subscription with no additional fees on top of what you already pay.
• Code ownership out of the box: generated Manim code is yours to export, version-control, and reuse without any platform lock-in.
• Lower barrier to entry: no Manim knowledge required and no server setup or Docker container to run.

See what’s new in each release on the Animo changelog.

💻 Models

Models are the core of Generative Manim. A model is a way to convert text to code, that can later be rendered in a video.

Name	Description	Engine	Phase
GM GPT-6 Astra	Most capable model for complex reasoning and coding	gpt-6-astra	✅
GM GPT-5.6 Sol	OpenAI’s frontier model for complex professional and coding work	gpt-5.6-sol	✅
GM GPT-5.6 Terra	Default OpenAI model, balances intelligence and cost	gpt-5.6-terra	✅
GM GPT-5.6 Luna	Fastest, most cost-efficient OpenAI tier	gpt-5.6-luna	✅
GM GPT-4o	Latest GPT model from OpenAI powered by a custom System Prompt	GPT-4o	✅
GM o1-mini	Compact OpenAI reasoning model	o1-mini	✅
GM GPT-3.5 Fine Tuned	First Fine-tuned model of GPT-3.5	GPT-3.5	✅
GM GPT-3.5 Physics Fine Tuned	Fine-tuned GPT-3.5 model trained to generate Physics animations	GPT-3.5	✅
GM Claude Sonnet	Claude Sonnet 3 model from Sonnet adapted with our custom System Prompt	claude-3-sonnet-20240229	✅
GM Claude Sonnet 3.5	Claude Sonnet 3.5 model from Sonnet adapted with our custom System Prompt	claude-3-5-sonnet-20241022	✅
GM Claude Sonnet 4.6	Claude Sonnet 4.6 adapted with our custom System Prompt	claude-sonnet-4-6	✅
GM Claude Sonnet 5	Default Anthropic model, best combination of speed and intelligence	claude-sonnet-5	✅
GM Claude Opus 4.7	Claude Opus 4.7 for highest-quality Anthropic generation	claude-opus-4-7	✅
GM Claude Opus 4.8	Highest capability, state of the art on long-horizon agentic work	claude-opus-4-8	✅
GM Claude Haiku 4.5	Claude Haiku 4.5 for fast, lightweight Anthropic generation	claude-haiku-4-5-20251001	✅
GM Claude Fable 5	Most capable Anthropic model, for the most demanding reasoning	claude-fable-5	✅
GM Featherless Open Models	OpenAI-compatible access to hosted open-weight models via Featherless	Qwen, DeepSeek, CodeLlama, etc.	✅
GM LiteLLM Passthrough	Accepts any model string supported by LiteLLM (e.g. openai/gpt-4o)	litellm	✅
GM Gemini 2.5 Flash	Google’s Gemini 2.5 Flash accessed via google-genai SDK	gemini-2.5-flash	✅
GM Gemini 2.5 Pro	Google’s Gemini 2.5 Pro accessed via google-genai SDK	gemini-2.5-pro	✅
GM Gemini 3 Flash	Google’s Gemini 3 Flash preview accessed via google-genai SDK	gemini-3-flash-preview	✅
GM Gemini 3.7 Flash	Google’s latest and most capable Flash model, built for coding and agentic workflows	gemini-3.7-flash	✅
GM Kimi K3	Moonshot AI’s flagship model, 1M-token context with always-on thinking mode	kimi-k3	✅
GM Kimi K2.7 Code	Moonshot AI’s coding-specialized agentic model	kimi-k2.7-code	✅
GM Qwen 2.5 Coder 7B	Open-source model fine-tuned with SFT + DPO + GRPO pipeline	Qwen2.5-Coder-7B-Instruct	🚧
GM DeepSeek Coder V2 Lite	Open-source model fine-tuned with SFT + DPO + GRPO pipeline	DeepSeek-Coder-V2-Lite	🚧
GM CodeLlama 7B	Open-source model fine-tuned with SFT + DPO + GRPO pipeline	CodeLlama-7b-Instruct	🚧

📡 New Models

If you want to suggest a new model, please open an issue in the repository or talk with us in our Discord server.

🧠 Training Pipeline

We’re training open-source models to generate Manim code using a 3-stage pipeline that distills from GPT-4o:

1. SFT (Supervised Fine-Tuning): Train on 5,000+ validated prompt→code pairs
2. DPO (Direct Preference Optimization): Learn from render success/failure pairs
3. GRPO (Group Relative Policy Optimization): RL with the Manim renderer as a deterministic reward signal

The key insight: Manim is a deterministic verifier: code either renders or crashes. This replaces the need for a reward model, similar to how DeepSeek-R1 uses math answer checkers.

Base models: Qwen 2.5 Coder 7B, DeepSeek Coder V2 Lite, CodeLlama 7B. All use QLoRA (4-bit) to fit on free Kaggle T4 GPUs.

📏 Benchmark

Generative Manim now includes an executable benchmark MVP for expert Manim code generation under training/benchmarks.

The benchmark is built around the right primitives for programming evaluation:

• a frozen task suite
• render-based scoring
• Manim-specific structural checks
• pass@k for stochastic code generation
• reproducible JSONL and JSON reports

Start here:

cd training
python -m benchmarks.run export \
  --suite benchmarks/tasks/core_v1.jsonl \
  --output ./outputs/benchmarks/core_v1_prompts.jsonl

Then use the generated prompt file with python -m eval.generate_responses ..., or run the full flow with:

bash ./scripts/run_benchmark.sh qwen2.5-coder-7b ./outputs/grpo/qwen2.5-coder-7b benchmarks/tasks/core_v1.jsonl grpo 5 0.8 1,5

See training/benchmarks/README.md for the benchmark design and workflow.

Once you have multiple benchmark runs, compare them with:

cd training
python -m benchmarks.compare --results-dir ./outputs/benchmarks --suite core_v1

Or run a whole benchmark matrix from a manifest:

cd training
python -m benchmarks.matrix --manifest benchmarks/manifests/open_source_core_v1.json --dry-run

You can also benchmark hosted open-weight models through Featherless:

export FEATHERLESS_API_KEY="your-featherless-key"
cd training
python -m benchmarks.matrix --manifest benchmarks/manifests/featherless_core_v1.json --only qwen2.5-coder-7b-instruct-featherless

See docs/featherless.md for API usage, smoke tests, and the full Featherless benchmark workflow.

✨ Sponsors

Generative Manim is currently sponsored by The Astronomical Software Company.

🙌 Contributors

Thank you to everyone who has contributed to Generative Manim!

Contributor	Contribution
@abdullahsohaill	Add Gemini 2.5 Flash and Gemini 3 Flash support via google-genai
@tranquac	Fix command injection vulnerability in ffmpeg video export
@Wing900	Add Chinese README translation
@Puiching-Memory	Formatter, config, and tooling improvements
@RheagalFire	Add LiteLLM as AI gateway engine and streaming/edge case tests

🤲 Contributing

Generative Manim is an open source project.

If you want to be the author of a new feature, fix a bug or contribute with something new.

Fork the repository and make changes as you like. Pull requests are warmly welcome. Remember you can also join our Discord server to discuss new features, bugs or any other topic.