# Grok Imagine 1.5 Grok Imagine 1.5 is xAI's newer video model, generally available since 16 June 2026. In Sloosh it makes clips of up to 15 seconds with sound at up to 1080p, from text, a start and end frame, or up to 14 reference images. xAI says it brings better motion and physics, and clearer, better-synced speech. Web page: https://sloosh.ai/models/grok-imagine-1.5 [Use Grok Imagine 1.5](https://sloosh.ai/studio/video?video-model=grok-imagine-1.5) ## Key facts in Sloosh | | | | --- | --- | | Made by | xAI | | Makes | video (with sound: always) | | Inputs | text, start frame (optional), end frame (optional), up to 14 reference images (frames and references can be combined) | | Length | 4, 6, 8, 10 or 15 seconds | | Resolution | 480p, 720p, 1080p | | Aspect ratios | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 | | Prompt limit | 5,000 characters | ## Best for - Talking clips: xAI says "Sound effects, ambience, and dialogue are generated in the same pass and land on the action," with clearer, better-synced speech ([xAI](https://x.ai/news/grok-imagine-video-1-5)). - Action with weight: xAI says "Movement holds together over the length of a clip," with fewer warps ([xAI](https://x.ai/news/grok-imagine-video-1-5)). - Multi-subject scenes from many references: xAI's reference-to-video takes up to 14 images on 1.5 ([xAI](https://docs.x.ai/developers/model-capabilities/video/reference-to-video)). - Clips that must start and end on set images: xAI supports pinned first and last frames on 1.5 only ([xAI](https://docs.x.ai/developers/model-capabilities/video/generation)). - Product ads in several ratios, including 21:9. ## How to use Grok Imagine 1.5 in Sloosh 1. Open [Video in Studio](https://sloosh.ai/studio/video?video-model=grok-imagine-1.5) with Grok Imagine 1.5 in the model chip. 2. Add a start frame, an end frame, reference images (up to 14), or any mix of them. Or go text only. 3. Pick the length, resolution (1080p is xAI's native text- and image-to-video output) and aspect ratio. 4. Write the prompt with the action, camera and any dialogue in quotes. 5. Press Generate. The exact price shows on the button first. ## Grok Imagine 1.5 prompting tips - Give each reference one role and a fixed place in the scene; keep the cast small and props static with many references ([xAI](https://docs.x.ai/developers/model-capabilities/video/reference-to-video)). - When a first frame is pinned, it counts as the first image, so your references start at the next number ([xAI](https://docs.x.ai/developers/model-capabilities/video/reference-to-video)). - With an image, references or frames, the prompt is optional on 1.5; with text only it is required ([xAI](https://docs.x.ai/developers/model-capabilities/video/generation)). - More complex scenes take longer to process, so keep drafts simple ([xAI](https://docs.x.ai/developers/model-capabilities/video/generation)). ## Grok Imagine 1.5 example prompts **Prompt 1** ```text A barista in a green apron looks up from the espresso machine and says, warmly, "Your oat latte, extra hot." She slides the cup across the counter. Medium shot, slow push-in, morning café light. Sound: milk steaming, low café chatter. ``` **Prompt 2** ```text Start on the closed laptop from the start frame; it opens and the screen lights the desk, ending on the end frame. Slow orbit, soft blue light. Sound: a soft hinge click, a gentle chime. ``` **Prompt 3** ```text The model from Image 1 wears the scarf from Image 2 and the coat from Image 3, walking through falling snow on a city street at night. Wide 21:9 tracking shot. Sound: footsteps in snow, distant traffic. ``` ## How it compares in Sloosh | | Grok Imagine 1.5 | Grok Imagine | Kling 4.0 | | --- | --- | --- | --- | | Length | up to 15 s | up to 10 s | 5, 10, 15 or 30 s | | Reference images | 14 | 7 | 10 (plus 5 videos) | | Frames | start and end | start only | start and end | | Resolution | up to 1080p | up to 720p | 720p, 1080p | | Sound | always | always | always | ## Where else it runs - xAI API; Video 1.5 Fast on grok.com/imagine and the Grok iOS and Android apps ([xAI](https://x.ai/news/grok-imagine-video-1-5), 16 Jun 2026). ## Frequently asked questions ### What's new in Grok Imagine 1.5? xAI says it has "better motion, better physics, better audio," with sound effects, ambience and dialogue made in the same pass ([xAI](https://x.ai/news/grok-imagine-video-1-5)). ### When was Grok Imagine 1.5 released? xAI made Grok Imagine Video 1.5 generally available on 16 June 2026 and added reference images and native 1080p on 31 July 2026 ([xAI](https://x.ai/news/grok-imagine-video-1-5), [xAI](https://x.ai/news/grok-imagine-video-1-5-references)). ### Can Grok Imagine 1.5 make 1080p? Yes, Sloosh offers 480p, 720p and 1080p. xAI renders 1080p natively for text- and image-to-video; reference-to-video goes up to 720p ([xAI](https://docs.x.ai/developers/model-capabilities/video/generation)). ### How many reference images does Grok Imagine 1.5 take? Up to 14 in Sloosh, matching xAI's reference-to-video docs. ### How long can a Grok Imagine 1.5 clip be? 4, 6, 8, 10 or 15 seconds in Sloosh. ### Does Grok Imagine 1.5 support a last frame? Yes. Sloosh offers optional start and end frames, which xAI supports on 1.5 only. ### Grok Imagine vs Grok Imagine 1.5? 1.5 adds end frames, 15-second clips, 1080p and up to 14 references in Sloosh; the classic model tops out at 10 seconds, 720p and 7 references. ## Related - Models: [Grok Imagine](https://sloosh.ai/models/grok-imagine), [Kling 4.0](https://sloosh.ai/models/kling-4.0), [Happy Horse 1.1](https://sloosh.ai/models/happy-horse-1.1) - Spaces: [Cinematic Ad Sequence](https://sloosh.ai/spaces/cinematic-ad-sequence), [Ugc selfie video ad](https://sloosh.ai/spaces/ugc-selfie-video-ad) - Docs: [Grok Imagine](https://sloosh.ai/docs/grok-imagine.md) - Answers: [What is the best AI video model in 2026?](https://geo.sloosh.ai/posts/what-is-the-best-ai-video-model-in-2026) ## Sources - [xAI: Grok Imagine Video 1.5](https://x.ai/news/grok-imagine-video-1-5) - [xAI: Imagine Video 1.5 with References](https://x.ai/news/grok-imagine-video-1-5-references) - [xAI: Video generation](https://docs.x.ai/developers/model-capabilities/video/generation) - [xAI: Reference to video](https://docs.x.ai/developers/model-capabilities/video/reference-to-video)