Model reference · open weights

wan

wan is an open-weight video model from calcuis, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Video calcuis 1 variants 39k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What wan is

gguf quantized version of wan 1.3b models - run it straight with gguf-connector - opt a gguf file in the current directory to interact with by: GGUF file(s) available. Select which one to use: 1. wan2.1-t2v-1.3b-q40.gguf 2. wan2.1-t2v-1.3b-q80.gguf 3. wan2.1-vace-1.3b-q40.gguf 4. wan2.1-vace-1.3b-q80.gguf Enter your choice (1 to 4): run it with gguf-node via comfyui - drag wan to ./ComfyUI/models/diffusionmodels - drag umt5 to ./ComfyUI/models/textencoders - drag pig to ./ComfyUI/models/vae review - wan architecture; should work on both comfyui-gguf and gguf nodes - full set gguf works right away (model + encoder + vae); gguf node is recommended for full gguf - vace model is recommended, since it doesn't need vision clip to work (for i2v and v2v) and run faster than fun model a lot, according to the initial test results - upgrade your node for umt5 gguf encoder support - note: for umt5 gguf, you might encounter oom after rebuilding your tokenizer in the first prompt (once built the tokenizer alive during the session; before you kill it); don't panic, prompt again it should work reference - base model from wan-ai - comfyui from comfyanonymous - comfyui-gguf city96 (special thanks; fully compatible) - pig architecture from connector - gguf-node (pypi|repo|pack) - gguf-connector (pypi)

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

Specifications

What it is

Makercalcuis
TypeVideo models
Variants1
Based onWan-AI/Wan2.1-VACE-1.3B, Wan-AI/Wan2.1-T2V-1.3B
Released2025-03-14
Popularity39k downloads / month
Likes205
LicenceOpen weights

How it works

How video models work

Prompt / imagestart pointTemporal diffusionframes over timeVideoMP4 clipA video model generates a sequence of coherent frames from your prompt or a starting image.

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.

VariantParamsPrecisionVRAMFits 16 GBWeights
wan-1.3b-ggufGGUFWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys wan for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wan 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":"wan","prompt":"a drone shot over a forest"}'

Details

Languages, data & research

Languages

en

Tags

gguf gguf-node gguf-connector text-to-video en doi:10.57967/hf/4819

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want wan on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More video models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms