ltxv

About

What ltxv is

GGUF quantized and fp8 scaled versions of LTX-Video - run it with gguf-connector; simply execute the command below in console/terminal GGUF file(s) available. Select which one to use: 1. ltxv-2b-0.9.8-distilled-iq4nl.gguf 2. ltxv-2b-0.9.8-distilled-q6k.gguf 4. ltxv-2b-0.9.8-distilled-q80.gguf Enter your choice (1 to 3): - opt a gguf file in your current directory to interact with; nothing else note: for the latest update, should be able to adjust number of steps, i.e., for distilled model, use 15 instead of 30; save a lot of loading time run it with gguf-node via comfyui - drag ltx-video-2b-v0.9.1-r2-q40.gguf (1.09GB) to ./ComfyUI/models/diffusionmodels - drag t5xxlfp16-q40.gguf (2.9GB) to ./ComfyUI/models/textencoders - drag ltxvvaefp32-f16.gguf (838MB) to ./ComfyUI/models/vae run it straight (no installation needed way) - run the .bat file in the main directory (assuming you are using the gguf-node pack below) - drag the workflow json file (below) to your browser workflow - example workflow for gguf (see demo above) - example workflow for the original safetensors review - q2k gguf is super fast but not usable; keep it for testing only - surprisingly 0.9fp8e4m3fn and 0.9-vaefp8e4m3fn are working pretty good - mix-and-match possible; you could mix up using the vae(s) available with different model file(s) here; test which combination works best - you could opt to use the t5xxl scaled safetensors or t5xxl gguf (more quantized versions of t5xxl can be found here) as text encoder - new set of enhanced vae (from fp8 to fp32) added in this pack; the low ram version gguf vae is also available right away; upgrade your node for the new feature: gguf vae loader - gguf-node is available (see details here) for running the new features (the point below might not be directly related to the model) - you are able to make your own fp8e4m3fn scaled safetensors and/or convert it to gguf with the new node via comfyui run it with diffusers🧨 (alternative 1) run it with gguf-connector (alternative 2: auto-mode) - simply execute the command below in console/terminal - note: during the first time launch, it will pull the model file(s) to local cache automatically; then opt to run it en

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How video models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys ltxv for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (ltxv below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/videos/generations \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"ltxv","prompt":"a drone shot over a forest"}'

Details

Languages, data & research

Licence

Commercial licence needed

Sources

Weights & code

Explore

More video models