# Veo 3.1 Lite, Grok Imagine Image, and Wan 2.7

By Steven Van · 2026-04-06

Veo 3.1 Lite and Wan 2.7 add video, Grok Imagine Image adds image generation, all selectable from Higgsfield's Video and Image tabs.

Higgsfield added three models to its model selector: Veo 3.1 Lite from Google, Grok Imagine Image from xAI, and Wan 2.7 from Alibaba. The [changelog entry](<https://higgsfield.ai/creator-hub/changelog#veo-3-1-lite-grok-imagine-image-and-wan-2-7>) lists what each one supports.

## Veo 3.1 Lite

Google's fast video model generates at 720p or 1080p, up to 8 seconds. It handles text-to-video and image-to-video, both with native audio.

## Grok Imagine Image

xAI's image model covers photorealistic and stylized text-to-image generation, style transfer, and multi-image editing.

## Wan 2.7

Alibaba's video model outputs 1080p video up to 15 seconds. Listed capabilities:

- First and last frame control

- 9-grid input

- Native audio

- Instruction-based editing

- Multi-reference support

## Where to find them

In [Higgsfield](<https://creatorstoolbox.com/tools/higgsfield>), open Video or Image and pick the model from the model selector.

![Higgsfield](<https://higgsfield.ai/icon.png>)

Higgsfield

AI video and image generation platform — create videos, edit with motion control, swap faces, and collaborate in real time.

[View Higgsfield →](<https://creatorstoolbox.com/tools/higgsfield>)

Sources

[Original source](<https://higgsfield.ai/creator-hub/changelog#veo-3-1-lite-grok-imagine-image-and-wan-2-7>)

[Read Veo 3.1 Lite, Grok Imagine Image, and Wan 2.7 on Creators Toolbox](<https://creatorstoolbox.com/blog/higgsfield-veo-3-1-lite-grok-imagine-image-and-wan-2-7>)

---
Canonical source: https://creatorstoolbox.com/blog/higgsfield-veo-3-1-lite-grok-imagine-image-and-wan-2-7