> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vivix.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Changelog

## W 1.1

November 6, 2026

### Model Features

* **Auto mode.** W1 Auto selects a generation speed automatically, making it easier to get started without choosing a speed for each request.
* **Video references.** Use a reference video to guide motion, camera movement or visual style, alongside your prompt, images and audio.
* **More natural faces.** Improved skin texture and facial highlights reduce the overly glossy look.

<video controls playsInline preload="none" poster="/images/changelog/w1-1-face-detail.webp" aria-label="W 1.1 facial detail example" src="https://platform.vivix.ai/vivix-w1-model/assets/face-study.mp4" />

**More natural faces**Skin texture, expressions and highlights as the lighting changes.

<video controls playsInline preload="none" poster="/images/changelog/w1-1-video-reference.webp" aria-label="W 1.1 cat cooking with video reference" src="https://platform.vivix.ai/vivix-w1-model/assets/reference-cat-fried-rice.mp4" />

**Video reference: cat cooks fried rice**A new subject follows the cooking actions from a reference video.

### API Updates

* **Auto:** set `model` to `vivix-w1-auto` when submitting a video generation job.
* **Video upload:** upload reference videos with `POST /v1/files/videos`.
* **Video input:** pass the upload response's `data.url` in `jobs[].ref_videos` as an array of `{ "url": "<UPLOADED_VIDEO_URL>" }` objects. Describe what to borrow from each video in your `prompt`. Video references cannot be combined with `first_frame_image` or `last_frame_image`.

[See the video reference request example and field details →](https://docs.vivix.ai/video-generation/world-video-generation.md#video-reference-to-video)

***

## W 1.0

October 9, 2026

### Model Features

**W 1.0 is officially released, bringing low-cost, fast video generation to creators and developers.** Create more variations and iterate on your ideas with three generation speeds: **Normal**, **Fast** and **Ultra Fast**.

<video controls playsInline preload="none" poster="/images/changelog/w1-0-sneakers.webp" aria-label="W 1.0 sneakers on a sunlit court" src="https://platform.vivix.ai/vivix-w1-model/assets/scene-sneakers-w1-20261010-web.mp4" />

**Sneakers**Close-up tracking follows each step across a sunlit court.

<video controls playsInline preload="none" poster="/images/changelog/w1-0-potato-chip-ad.webp" aria-label="W 1.0 potato chip advertisement example" src="https://platform.vivix.ai/vivix-w1-model/assets/scene-chips-w1-20261010-web.mp4" />

**Potato chip ad**Product details and dynamic movement in a short commercial.

### API Updates

Select a model option using the `model` field:

| Model option | `model` value |
| - | - |
| Normal | `vivix-w1` |
| Fast | `vivix-w1-fast` |
| Ultra Fast | `vivix-w1-ultrafast` |

Submit a job with `POST /v1/videos/jobs`, then query its status with `GET /v1/videos/jobs/{job_id}` to retrieve the generated video.

[Read the World Video Generation guide →](https://docs.vivix.ai/video-generation/world-video-generation.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.