# Stable Video Diffusion (img2vid-XT) requirements

Updated: 2026-06-15

1.5B UNET video model, released 2023-11.

- Peak VRAM: ~8 GB at fp16 + offload (~22 GB all-resident)
- Offload floor: ~8 GB, much slower
- Resolution: 1024×576
- Tools: ComfyUI, Diffusers
- License: Stable Video Diffusion Community License (commercial use: conditional)
- Runs on 21 of 39 tracked devices

Sources: https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt, https://huggingface.co/docs/diffusers/using-diffusers/svd
More: https://localmodel.run/model/stable-video-diffusion