From f6eebfdcd2b0d790f381ab286592fe307ccc9c96 Mon Sep 17 00:00:00 2001 From: "openclaw-docs-sync[bot]" Date: Sat, 25 Apr 2026 17:17:34 +0000 Subject: [PATCH] chore(sync): mirror docs from openclaw/openclaw@67506ac2a9c51999e3254fbc95ab09aab530e2c4 --- .openclaw-sync/source.json | 4 ++-- docs/providers/xai.md | 10 ++++++---- docs/tools/video-generation.md | 8 +++++--- 3 files changed, 13 insertions(+), 9 deletions(-) diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json index 65bb5e8bc..2c052ebc8 100644 --- a/.openclaw-sync/source.json +++ b/.openclaw-sync/source.json @@ -1,5 +1,5 @@ { "repository": "openclaw/openclaw", - "sha": "768bbc7cc00bd550f22c9463d4da4f0fabbab038", - "syncedAt": "2026-04-25T17:15:08.374Z" + "sha": "67506ac2a9c51999e3254fbc95ab09aab530e2c4", + "syncedAt": "2026-04-25T17:16:01.030Z" } diff --git a/docs/providers/xai.md b/docs/providers/xai.md index 31551a381..b8221a11d 100644 --- a/docs/providers/xai.md +++ b/docs/providers/xai.md @@ -132,12 +132,14 @@ Legacy aliases still normalize to the canonical bundled ids: `video_generate` tool. - Default video model: `xai/grok-imagine-video` - - Modes: text-to-video, image-to-video, remote video edit, and remote video - extension + - Modes: text-to-video, image-to-video, reference-image generation, remote + video edit, and remote video extension - Aspect ratios: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3` - Resolutions: `480P`, `720P` - - Duration: 1-15 seconds for generation/image-to-video, 2-10 seconds for - extension + - Duration: 1-15 seconds for generation/image-to-video, 1-10 seconds when + using `reference_image` roles, 2-10 seconds for extension + - Reference-image generation: set `imageRoles` to `reference_image` for + every supplied image; xAI accepts up to 7 such images Local video buffers are not accepted. Use remote `http(s)` URLs for diff --git a/docs/tools/video-generation.md b/docs/tools/video-generation.md index c62af2c1d..48fefb4e1 100644 --- a/docs/tools/video-generation.md +++ b/docs/tools/video-generation.md @@ -97,7 +97,7 @@ Duplicate prevention: if a video task is already `queued` or `running` for the c | Runway | `gen4.5` | Yes | 1 image | 1 video | `RUNWAYML_API_SECRET` | | Together | `Wan-AI/Wan2.2-T2V-A14B` | Yes | 1 image | No | `TOGETHER_API_KEY` | | Vydra | `veo3` | Yes | 1 image (`kling`) | No | `VYDRA_API_KEY` | -| xAI | `grok-imagine-video` | Yes | 1 image | 1 video | `XAI_API_KEY` | +| xAI | `grok-imagine-video` | Yes | 1 first-frame image or up to 7 `reference_image`s | 1 video | `XAI_API_KEY` | Some providers accept additional or alternate API key env vars. See individual [provider pages](#related) for details. @@ -150,7 +150,9 @@ Role hints are forwarded to the provider as-is. Canonical values come from the `VideoGenerationAssetRole` union but providers may accept additional role strings. `*Roles` arrays must not have more entries than the corresponding reference list; off-by-one mistakes fail with a clear error. -Use an empty string to leave a slot unset. +Use an empty string to leave a slot unset. For xAI, set every image role to +`reference_image` to use its `reference_images` generation mode; omit the role +or use `first_frame` for single-image image-to-video. ### Style controls @@ -326,7 +328,7 @@ entries. - Supports text-to-video, image-to-video, and remote video edit/extend flows. + Supports text-to-video, single first-frame image-to-video, up to 7 `reference_image` inputs through xAI `reference_images`, and remote video edit/extend flows.