Overview - Ai

ai

7 days30 days

Latest CI Pipeline Executions

Fuzzy

Succeeded
705-featai-grok-video-generation-adapter-for-the-grok-imagine-video-models
b6ec1b46 feat(examples): provider optgroups in video model dropdown, use grok-imagine-video-1.5-preview Groups the video model dropdown by provider (fal.ai / xAI direct) the same way the image generator does, adds the model version to the direct-xAI entry names, and switches them to the grok-imagine-video-1.5-preview model. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
by Tom Beckenham
Succeeded
705-featai-grok-video-generation-adapter-for-the-grok-imagine-video-models
b6ec1b46 Merge c6e1573e5d10beb40843355011542dac958b9519 into ff267a5536327b006979f9f28ce2df7cc27f6e23
by Tom Beckenham
Succeeded
705-featai-grok-video-generation-adapter-for-the-grok-imagine-video-models
42a0e5f7 feat(examples): add direct-xAI grok video entries to ts-react-media Adds 'xAI Direct' text-to-video and image-to-video entries to the video generator that use the native grokVideo adapter against xAI's Imagine API (XAI_API_KEY), alongside the existing fal-hosted grok-imagine entries. Polling is now keyed by the UI model id (the direct entries share one adapter model), and the completed card shows the exact USD cost when the adapter reports it. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
by Tom Beckenham
Succeeded
705-featai-grok-video-generation-adapter-for-the-grok-imagine-video-models
42a0e5f7 Merge 49a7c09ac981889b979599c7b87a14ca5efdc93d into ff267a5536327b006979f9f28ce2df7cc27f6e23
by Tom Beckenham
Succeeded
705-featai-grok-video-generation-adapter-for-the-grok-imagine-video-models
dd449075 feat(ai-grok): video generation adapter for the grok-imagine video models Adds a grokVideo adapter to @tanstack/ai-grok for xAI's Imagine video models (grok-imagine-video at $0.05/s, grok-imagine-video-1.5-preview at $0.08/s) using the experimental generateVideo() jobs/polling architecture: POST /v1/videos/generations to create, GET /v1/videos/{request_id} to poll, hosted mp4 URL plus usage (billed seconds + exact USD cost) on completion. Sizing follows the grok-imagine aspect-ratio template ('16:9_720p' → aspect_ratio/resolution); durations are 1-15 integer seconds; image-to-video starting frames go through modelOptions.image. The Imagine video endpoints are plain JSON (not in the OpenAI SDK), so the adapter issues direct requests with an injectable fetch seam. Closes #705. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
by Tom Beckenham
Succeeded
705-featai-grok-video-generation-adapter-for-the-grok-imagine-video-models
dd449075 Merge 7d63f7a2415a05537cbba04f12d95e4f00ebb349 into ff267a5536327b006979f9f28ce2df7cc27f6e23
by Tom Beckenham