Model reference · open weights

Wan2.1-I2V-480P-Lightning

Video magespace Image→video 1 build Open weights 2k dl/mo

Wan2.1-I2V-480P-Lightning is an open-weight video model from magespace. Wan2.1-I2V-14B-480P-Lightning-Diffusers (BF16) weighs 45.7 GB; the smallest configuration that runs it is L40S 48 GB.

  • Wan2.1-I2V-480P-Lightning is an image-to-video model developed by magespace that generates 480P videos from input images.
  • It features 16.4B parameters and supports English and Chinese languages.
  • The model is released under the apache-2.0 license.

Summary of the magespace/Wan2.1-I2V-14B-480P-Lightning-Diffusers model card, 2026-10-01

What it is

Released bymagespace
Released2025-08-14
Parameters16.4B
VRAM45.7 GB for the weights

What it runs on

Memory and cards for Wan2.1-I2V-14B-480P-Lightning-Diffusers (BF16)

45.7 GBweights, file size
32.8 GBbiggest part
537 MBruntime overhead
CardWeightsMemory
RTX 3060 12 GB … RTX 5090 32 GBdoes not fit
L40S 48 GBfits (encoders offloaded)44.0 GB
A100 80 GBfits78.2 GB
H100 80 GBfits78.1 GB
RTX PRO 6000 Blackwell 96 GBfits93.8 GB
DGX Spark (GB10) 128 GB unifiedfits107 GB
H200 141 GBfits138 GB
B200 180 GBfits176 GB

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.

Running it yourself

Run it on a rented GPU

Rent a machine by the hour. Runs as it is with diffusers, on the machine, in Python.

# on your rented machine: pip install diffusers transformers accelerate ftfy
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import export_to_video

pipe = DiffusionPipeline.from_pretrained("magespace/Wan2.1-I2V-14B-480P-Lightning-Diffusers", torch_dtype=torch.bfloat16).to("cuda")
frames = pipe(prompt="a drone shot over a forest at sunrise").frames[0]
export_to_video(frames, "/workspace/out.mp4", fps=16)
Renting a GPU: connect, tunnels, Python
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms