DEDUPED Hot AI repos, turned into use cases Get 5 a day

What you can do with Agent Garten

AgentGarten is a Python repo with a neural renderer that turns depth and surface-normal data into video, plus training and streaming inference code; its code worlds and agent practice loop are not released yet.

Trended earlier

MirroS-Lab/AgentGarten on GitHub

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

What do you want to do?

4 use cases

  • Render comparison videos from a renderer checkpoint

    Check a renderer checkpoint visually by writing validation videos without training.

    View prompt
    Using the AgentGarten repo at <repo path>, set up the environment, download the weights listed in the README, and render the validation clips of the checkpoint at <checkpoint path> without training. Expected output: comparison videos (depth, normal, ground truth, sample) under samples/. Verify that the samples/ folder contains one video set per validation clip before reporting success.

  • Generate renderer video block by block with streaming

    Run the renderer one block at a time with a bounded KV cache for step-by-step generation.

    View prompt
    Using the AgentGarten repo at <repo path>, write and run a script that streams the renderer block by block with Cosmos3Stream for the first-frame anchor at <anchor latent path>. Expected output: a sequence of committed blocks for the conditions in <conditions path>. Verify that the number of committed blocks equals the number of condition blocks before reporting success.

  • Train the renderer on your own depth and normal clips

    Fine-tune the neural renderer on your own clips listed in a JSONL manifest.

    View prompt
    Using the AgentGarten repo at <repo path>, create a JSONL manifest from the clips in <clips folder> with depth and normal files, then launch bidirectional training with scripts/run.sh. Expected output: training logs and checkpoints written under the output root in .env. Verify that the manifest has one valid line per clip and that the first training iteration starts before reporting success.

  • Decode renderer RGB preview faster with TAEHV

    Attach the TAEHV decoder to speed up RGB output while encoding stays on the Wan encoder.

    View prompt
    Using the AgentGarten repo at <repo path>, add the TAEHV decoder override for the file at <taew2_2_super.pth path> and render the validation clips. Expected output: the same comparison videos under samples/, with RGB decoded through the TAEHV decoder. Verify that the decoder path in the override exists on disk before reporting success.

How to use Agent Garten

  1. Check you have what it needs: A CUDA host with Python 3.11+ and PyTorch 2.9+; Access to the Hugging Face weights for Cosmos3-Nano and Wan2.2-TI2V-5B, plus disk space for them; Git and the hf command-line tool.
  2. Open MirroS-Lab/AgentGarten on GitHub and read the README and license.
  3. git clone https://github.com/MirroS-Lab/AgentGarten.git
  4. pip install -e '.[data,media,wandb,te]'
  5. cp .env.example .env
  6. Run hf download nvidia/Cosmos3-Nano --include 'transformer/*' 'text_tokenizer/*' 'assets/negative_prompt.json' --local-dir weights/Cosmos3-Nano and hf download Wan-AI/Wan2.2-TI2V-5B Wan2.2_VAE.pth --local-dir weights/Wan2.2-TI2V-5B, then set WM_COSMOS3_NANO and WM_WAN22_VAE in .env to those paths. (inferred, check the README)

These steps come from our top use case, Render comparison videos from a renderer checkpoint, which also has a copy-paste agent prompt.

Agent Garten alternatives · Best AI repos for Research

About this repo

Requirements

  • A CUDA host with Python 3.11+ and PyTorch 2.9+
  • Access to the Hugging Face weights for Cosmos3-Nano and Wan2.2-TI2V-5B, plus disk space for them
  • Git and the hf command-line tool
  • For training: a JSONL manifest of your own clips with depth and normal data
Maintain Agent Garten? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/mirros-lab-agentgarten.svg)](https://dedupedai.com/use-cases/mirros-lab-agentgarten/?ref=badge)

More badge styles and HTML

Questions about Agent Garten

What is Agent Garten?

AgentGarten is a Python repo with a neural renderer that turns depth and surface-normal data into video, plus training and streaming inference code; its code worlds and agent practice loop are not released yet. It is an open-source project on GitHub: https://github.com/MirroS-Lab/AgentGarten.

Who is Agent Garten for?

Written for ML researchers and engineers with a CUDA GPU who want to render, stream, or train the AgentGarten neural renderer.

What can I do with Agent Garten?

4 use cases so far, for example: Render comparison videos from a renderer checkpoint; Generate renderer video block by block with streaming; Train the renderer on your own depth and normal clips. Each has steps and a copy-paste agent prompt.

What do I need to run Agent Garten?

A CUDA host with Python 3.11+ and PyTorch 2.9+; Access to the Hugging Face weights for Cosmos3-Nano and Wan2.2-TI2V-5B, plus disk space for them; Git and the hf command-line tool; For training: a JSONL manifest of your own clips with depth and normal data.

What are alternatives to Agent Garten?

Other hot AI repos in Research: Scientific Agent Skills, Speaker Mem R1, DSH Council, Evo Bot, AI Engineering Course.

Is Agent Garten safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.