Instructions to use exeterminal/Exe-Motion-Dynamic-V1-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use exeterminal/Exe-Motion-Dynamic-V1-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Exe-Motion-Dynamic-V1-MLX exeterminal/Exe-Motion-Dynamic-V1-MLX
- LTX-2
How to use exeterminal/Exe-Motion-Dynamic-V1-MLX with LTX-2:
# Install the LTX-2 pipelines git clone https://github.com/Lightricks/LTX-2.git cd LTX-2 uv sync --frozen
# Download the weights from this repo, plus the Gemma text encoder hf download exeterminal/Exe-Motion-Dynamic-V1-MLX --local-dir models/Exe-Motion-Dynamic-V1-MLX hf download google/gemma-3-12b-it-qat-q4_0-unquantized --local-dir models/gemma-3-12b
# Fast pipeline (distilled model, no distilled LoRA needed) uv run python -m ltx_pipelines.distilled \ --distilled-checkpoint-path models/Exe-Motion-Dynamic-V1-MLX/<distilled-checkpoint>.safetensors \ --spatial-upsampler-path models/Exe-Motion-Dynamic-V1-MLX/<spatial-upsampler>.safetensors \ --gemma-root models/gemma-3-12b \ --prompt "A beautiful sunset over the ocean" \ --output-path output.mp4 # For image-to-video, add: --image path/to/image.jpg 0 0.8# HQ pipeline (two-stage, higher quality) uv run python -m ltx_pipelines.ti2vid_two_stages_hq \ --checkpoint-path models/Exe-Motion-Dynamic-V1-MLX/<checkpoint>.safetensors \ --distilled-lora models/Exe-Motion-Dynamic-V1-MLX/<distilled-lora>.safetensors 0.8 \ --spatial-upsampler-path models/Exe-Motion-Dynamic-V1-MLX/<spatial-upsampler>.safetensors \ --gemma-root models/gemma-3-12b \ --prompt "A beautiful sunset over the ocean" \ --output-path output.mp4 # For image-to-video, add: --image path/to/image.jpg 0 0.8 - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Exe Motion Dynamic V1
The video model of Exe Motion, built to run local on an Apple Silicon Mac. It is LTX-2.3 (22B distilled) with one change that matters on a 64 GB machine: the text encoder is quantized to 8-bit, so the part that used to be the memory spike of a run is now a quarter of its size. Website to the Main AI Agent Harness: https://exe-hq.net
Everything runs on-device through MLX — no cloud, no upload of your images or prompts.
What was quantized
The Gemma text encoder shipped in F32 and, at ~46 GB, was the biggest single thing a run had to hold. It is loaded, used to read the prompt, then freed before the transformer runs — so its size sets the peak. Quantizing it to 8-bit takes it to 12.5 GB, resident, without touching the transformer.
| Part | Before | After |
|---|---|---|
| Text encoder (Gemma) | 46 GB · F32 | 12.5 GB · 8-bit |
| Transformer (22B distilled) | 35 GB | 35 GB · unchanged |
| Whole model on disk | ~89 GB | ~55 GB |
The transformer is left at full precision on purpose: the runtime has no quantized path for it, and a quantized copy would not load. The encoder is where the win is, and it is the honest one.
What it does
Image-to-video and text-to-video at up to 720p. Frame count drives the length (24 fps); resolution is free in steps of 64. A distilled fast path keeps steps low; there is no separate turbo weight to install.
Recommended settings
- Resolution: 1280×704 is the default; drop it for longer clips or to save memory.
- Frames:
8n+1(81 ≈ 3.4 s, 121 ≈ 5 s). Longer needs more memory. - Apple Silicon: long runs on a 64 GB machine still benefit from raising the
Metal working-set limit before starting:
sudo sysctl iogpu.wired_limit_mb=59392.
Files
A whole, assembled build — nothing to convert or borrow:
transformer/ 22B distilled, bf16
text_encoder/ Gemma, 8-bit (this build's change)
text_projections/ connectors
vae/ audio_vae/ vocoder/ tokenizer/
License
Weights inherit the license of the base model, Lightricks/LTX-2.3. See the linked LICENSE for terms.
Model tree for exeterminal/Exe-Motion-Dynamic-V1-MLX
Base model
Lightricks/LTX-2.3