Grok Imagine 1.5
grok-imagine-1-5-text-to-video-private- - 🆕 xAI's 1.5 generation of the Grok Imagine video family.
- - 🎯 xAI's docs describe 1.5 preview as image-conditioned video generation.
- - 💬 Text-driven access to 1.5 appears in third-party API listings only.
- - ⚡ Fast configuration produces 6-second 720p clips in about 25 seconds.
- - 📏 The prior generation needed 40-plus seconds for that clip, per xAI.
- - 🔧 Request parameters cover duration, aspect ratio and resolution.
- - 👁️ 1080p output documented for 1.5 image-conditioned generation.
- - 🏢 Built by xAI.
xAI is an American artificial intelligence company and wholly owned subsidiary of SpaceX. The company develops AI systems under the Grok brand, spanning language models, image generation, and video synthesis. xAI has quickly established itself as a multimodal AI lab with…
Explore 14 more models by XAI (company) →Grok Imagine 1.5 is the second-generation entry in xAI's Imagine video line, following the original Grok Imagine video models released earlier in 2026. It is served through xAI's video generation API, where a request supplies a prompt plus parameters such as duration, aspect ratio and resolution, and the service returns a finished clip with synchronized audio.
Against its own predecessor, xAI reports improvements in motion, physics and audio quality alongside faster generation. The company states that the Fast configuration roughly doubles throughput, producing 6-second 720p videos in about 25 seconds compared with more than 40 seconds for the prior model. xAI's documentation also lists 1080p output for the 1.5 generation in image-conditioned mode, above the earlier resolution ceiling.
The 1.5 release appears in this catalog under several conditioning modes: this text-driven entry, the image-conditioned Grok Imagine 1.5, and the later Grok Imagine 1.5 R2V for reference-guided generation. Note that xAI's own preview documentation describes 1.5 as image-to-video, with text prompts handled by the base Imagine video model; text-driven 1.5 access is reported by third-party API listings rather than by xAI, so availability by mode may vary by endpoint.
For still images and editing, xAI ships separate models such as Grok Imagine and Grok Imagine for inpainting.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
Daily usage · Grok Imagine 1.5 · Organic sellers
| Seller | Health | Rep↓ | Sales | Video | Routing | $ / s | $ / video |
|---|---|---|---|---|---|---|---|
| Venice.ai Proxy 0x1f22…18c9 | failingupstream error · 3.7 h | 86.84 | $78.86 | 16 min | #1 | $0.0886 | — |
"Best price" and the seller table are live Antseed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = buyer trust score (0-100, the Antseed SDK's own formula). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on Antseed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.