media-agent 0.11.0: Grok Imagine on grok.com, 1080p on the subscription

plugins/media-agent/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "media-agent",
   "displayName": "Media Agent",
-  "version": "0.10.0",
+  "version": "0.11.0",
   "author": {
     "name": "4nrry",
     "url": "https://github.com/4nrry"

plugins/media-agent/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
   "name": "media-agent",
-  "version": "0.10.0",
+  "version": "0.11.0",
   "description": "Media production by an agent on a machine with an 8 GB GPU and commercial licensing, one skill per modality with rules that hold for any model: image and video generation, image retouching, voice-over at -16 LUFS, music and sound with per-item licenses, video composed as code, editing finished video, and a 3D product turntable. One hook warns where vipsthumbnail -o really writes.",
   "author": {
     "name": "4nrry",

plugins/media-agent/skills/video-generation/SKILL.md

@@ -21,7 +21,8 @@ scripts/contact-sheet.sh check.jpg still.png shot.mp4
 ```
 
 Google Flow runs Omni and Veo on the Google AI subscription's credits through a
-browser ([references/flow.md](references/flow.md)).
+browser ([references/flow.md](references/flow.md)), and grok.com's Imagine makes
+1080p on the Grok subscription ([references/grok-web.md](references/grok-web.md)).
 `scripts/omni.py` takes the same prompt and still on the Gemini API key, which
 bills every call; [references/tools.md](references/tools.md) marks what each
 route bills.

plugins/media-agent/skills/video-generation/references/grok-web.md

@@ -0,0 +1,47 @@
+# Grok Imagine on grok.com
+
+Checked on 2026-10-26, with one live run on the Ultra plan. Grok Imagine in the
+web app (grok.com/imagine) makes 1080p video on the Grok subscription's pool,
+which Grok Build and Hermes refuse (they stop at 720p). It has no API on the
+subscription: the xAI API bills apart from it.
+
+## Settings
+
+The prompt box switches between Image, Video and Agent. In Video mode:
+
+| Setting | Options |
+|---|---|
+| Resolution | 480p, 720p, 1080p |
+| Duration | 6 s, 10 s, 15 s |
+| Aspect ratio | 2:3, 3:2, 1:1, 9:16, 16:9 |
+
+It also takes a first and a last frame, makes seamless loops, and the result
+page offers Replace Audio, Regenerate, Captions and Share. A generation spends
+the pool at once: there is no cost prompt.
+
+## Driving it from an agent
+
+- Use a browser where the user is already signed in (the desktop app's browser
+  pane, Claude in Chrome, or a persistent Chrome profile under Playwright). The
+  user signs in; never type their password or answer a CAPTCHA. On a cookie
+  banner, reject the optional cookies.
+- Set Video, the resolution, the duration and the aspect ratio before typing the
+  prompt, and check them every time.
+- A still or a first and last frame from disk needs a browser tool that can
+  fill a file picker (Claude in Chrome's upload, Playwright's
+  `set_input_files`). The desktop app's browser pane cannot; there, prompt text
+  to video or have the user drop the file in.
+- Downloading is the user's call; the clip stays in the account's Imagine
+  library.
+
+## Measured
+
+One text-to-video run, 2026-10-26: 1080p, 6 s, 16:9, done in about 45 s. The
+page's player reported 1904x1072 and 6.04 s: 1080p class, not 1920x1080, so
+scale or crop it to the timeline's size in the edit.
+
+## Sources
+
+- The grok.com/imagine page itself, read in the browser on 2026-10-26.
+- x.ai, "Introducing The X Subscription": API usage is billed apart from the
+  subscription.

plugins/media-agent/skills/video-generation/references/tools.md

@@ -11,8 +11,9 @@ key's budget belongs to something else.
 | Tool | Billed to | Script | Good for | Notes |
 |---|---|---|---|---|
 | Gemini Omni (`gemini-omni-1.1-flash`), Gemini API | Gemini API key, per second | `python3 scripts/omni.py "<motion>" -o shot.mp4 --image still.png` | shots from a still, between a first and a last frame (`--last`), or of a subject from references (`--ref`); extending a clip (up to 40 s in total) and editing it in turns, through the API only | 360p or 720p native; 1080p and 4k are upscaled by Google; 16:9 or 9:16; no negative prompt and no duration setting: clips come back at 10 s, 24 fps, with an audio track (trim in the edit) |
-| Grok Imagine video, through Grok Build | Grok subscription | `scripts/grok-video.sh "<motion>" out.mp4 --image still.png` | backgrounds, small cards, Reels backdrops | 480p by default, `--res 720p` at most: on the subscription, both Grok Build's video tools and Hermes's refuse 1080p ("resolution_name must be one of: 480p, 720p"); 6 s clips with audio |
+| Grok Imagine video, through Grok Build | Grok subscription | `scripts/grok-video.sh "<motion>" out.mp4 --image still.png` | backgrounds, small cards, Reels backdrops | 480p by default, `--res 720p` at most: on the subscription, both Grok Build's video tools and Hermes's refuse 1080p ("resolution_name must be one of: 480p, 720p"), while the web app makes it ([grok-web.md](grok-web.md)); 6 s clips with audio |
 | Google Flow (web), Omni Flash and Veo 3.1 | Google AI Pro/Ultra credits | a browser, [flow.md](flow.md) | Omni and Veo without an API key: from a still, first and last frame, extend and edit in the app | 360p 8 s Omni costs 6 credits; no API, so a browser agent drives it with the user signed in |
+| Grok Imagine on grok.com (web) | Grok subscription | a browser, [grok-web.md](grok-web.md) | native 1080p on the subscription, 6, 10 or 15 s, first and last frame, loops | 1080p came back as 1904x1072; no API, so a browser agent drives it with the user signed in |
 | Grok Imagine API (`grok-imagine-video-1.5`, `-1.5-lite`) | xAI API key, per second (billed apart from the Grok subscription) | none bundled | native 1080p, 1–15 s, reference images | priced per second; needs an xAI API key |
 | Veo 3.1 GA (`veo-3.1-generate-001`, `-fast-`) | Google Cloud billing (Vertex) | none bundled | premium shots | only on Google's enterprise platform (Vertex), us-central1 |
 | ElevenLabs canvas (MCP) | ElevenLabs plan credits | `audio` skill | upscaling a clip (Topaz) | video models there cost a large share of a month's credits per clip |