makaron-cli 0.9.0 → 0.10.0

package/README.md

@@ -218,10 +218,11 @@ npx makaron-cli analyze --video input.mp4 "describe the key actions and pacing"
 
 # 3a. Submit image-to-video rendering (images must be public URLs from step 1 or uploaded)
 npx makaron-cli video create --script "Shot 1 (5s): <<<image_1>>> ..." --image https://...jpg --duration 5 --model kling
+npx makaron-cli video create --script "Shot 1 (5s): <<<image_1>>> slow cinematic push-in with native ambience" --image https://...jpg --duration 5 --model grok
 
 # 3b. Edit a video from a local file or public URL
-npx makaron-cli video create --script "make it funny" --video input.mp4 --duration 5 --model seedance
-npx makaron-cli video create --script "make it warmer and cinematic" --video https://example.com/input.mp4 --duration 5 --model seedance
+npx makaron-cli video create --script "make it funny" --video input.mp4 --duration 5 --model seedance-fast
+npx makaron-cli video create --script "make it warmer and cinematic" --video https://example.com/input.mp4 --duration 5 --model seedance --video-resolution 1080p
 
 # 4. Check status
 npx makaron-cli video status <taskId>
@@ -233,9 +234,9 @@ For project/timeline video editing, use:
 npx makaron-cli chat --project <id|auto> --video input.mp4 -b "make it funny"
 ```
 
-Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to 7), `--video <file|url>`, `--duration <seconds>`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`. SeeDance accepts integer output duration 4-15s (default 5s); Kling supports 5-15s.
+Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to 7), `--video <file|url>`, `--duration <seconds>`, `--aspect 9:16|16:9|1:1`, `--model seedance-fast|seedance|kling|grok`, `--video-resolution auto|480p|720p|1080p|4k`. Default model is `seedance-fast`. SeeDance accepts integer output duration 4-15s (default 5s); Kling supports 5-15s; Grok 1.5 supports 1-15s single-image-to-video only. For `--model grok`, forced `--aspect` is ignored to avoid xAI stretching the source image; pad/create the image at the target shape first or use another model.
 
-Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance --video` uses the Seedance video-reference path and requires target <=15s, <=50MB, width/height 300-6000px, aspect ratio 0.4-2.5, and frame pixels 409,600-2,086,876. Tiny metadata padding up to 15.5s is accepted and output duration is clamped to 15s.
+Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance-fast --video` or `--model seedance --video` uses the SeeDance video-reference path and requires target <=15s, <=50MB, width/height 300-6000px, aspect ratio 0.4-2.5, and frame pixels 409,600-2,086,876. Tiny metadata padding up to 15.5s is accepted and output duration is clamped to 15s. Grok does not support video references.
 
 ### `music` — Music generation
 
@@ -350,7 +351,7 @@ send_message "All done!"
 - One project = one conversation thread. All history is preserved.
 - One run at a time per project. New message interrupts previous run.
 - Multi-image: `create --image a.jpg --image b.jpg` or `chat --image ref.jpg`.
-- Videos take 2-5 minutes to render. Use `responses get <runId> --wait --json` for the default customer-service path.
+- Most videos take 3-5 minutes; Grok is usually around 30-40 seconds. Use `responses get <runId> --wait --json` for the default customer-service path.
 - Music takes ~60 seconds. Appears in output when done.
 - Images are typically ready in 15-30 seconds.
 - stdout is always machine-readable JSON/text. Human-friendly logs go to stderr.

package/bin/makaron.mjs

@@ -274,7 +274,8 @@ Options:
   --image <file|url>        Attach a reference image or screenshot. Repeatable.
   --video <file|url>        Attach a video to the project timeline. Repeatable.
   --model <name>            Preferred image/model route.
-  --video-model <name>      Preferred video model.
+  --video-model <name>      Preferred video model: seedance-fast, seedance, kling, or grok.
+  --video-resolution <res>  Video resolution: auto, 480p, 720p, 1080p, or 4k.
   --background, -b          Submit and print a runId.
   --json                    Output structured JSON.
   --stream                  Legacy live SSE stream.
@@ -441,6 +442,7 @@ async function submitRun(baseUrl, headers, projectId, prompt, opts = {}) {
   const body = { projectId, prompt };
   if (opts.preferredModel) body.preferredModel = opts.preferredModel;
   if (opts.videoModel) body.videoModel = opts.videoModel;
+  if (opts.videoResolution) body.videoResolution = opts.videoResolution;
   if (opts.currentSnapshotIndex != null) body.currentSnapshotIndex = opts.currentSnapshotIndex;
   if (opts.isNsfw) body.isNsfw = opts.isNsfw;
 
@@ -1113,12 +1115,12 @@ function printHelp(topic, subtopic) {
     console.log('Usage: makaron analyze --video <file|url> ["question"]');
   } else if (topic === 'video') {
     if (subtopic === 'script') console.log('Usage: makaron video script --image <file> [--image <file>] [--lang en|zh] "direction"');
-    else if (subtopic === 'create') console.log('Usage: makaron video create --script "..." (--image <url> | --video <public-url>) [--duration 10] [--aspect 9:16] [--model kling|seedance] [--keep-original-sound]');
+    else if (subtopic === 'create') console.log('Usage: makaron video create --script "..." (--image <url> | --video <public-url>) [--duration 10] [--aspect 9:16] [--model seedance-fast|seedance|kling|grok] [--video-resolution auto|480p|720p|1080p|4k] [--keep-original-sound]');
     else if (subtopic === 'status') console.log('Usage: makaron video status <taskId> | --snapshot <snapshotId> [--wait]');
     else console.log(`Video commands:
   video script --image <file> [--image <file>] "direction"   Write video script
   video create --script "..." --image <url> [--duration 10]  Submit video task
-  video create --script "..." --video <public-url> [--model kling|seedance]  Edit a video (standalone)
+  video create --script "..." --video <public-url> [--model seedance-fast|seedance|kling]  Edit a video (standalone; Grok does not support video refs)
   video status <taskId>                                      Check video status
   video status --snapshot <snapshotId> [--wait]              Check v2 video snapshot
 `);
@@ -1197,6 +1199,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
   let jsonOutput = false;
   let activeSkill = undefined;
   let videoModel = undefined;
+  let videoResolution = undefined;
   let preferredModel = undefined;
   for (let i = 1; i < args.length; i++) {
     if (args[i] === '--project' && args[i + 1]) projectId = args[++i];
@@ -1207,6 +1210,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
     else if (args[i] === '--background' || args[i] === '-b') background = true;
     else if (args[i] === '--json') jsonOutput = true;
     else if (args[i] === '--video-model' && args[i + 1]) videoModel = args[++i];
+    else if (args[i] === '--video-resolution' && args[i + 1]) videoResolution = args[++i];
     else if (args[i] === '--model' && args[i + 1]) preferredModel = args[++i];
     else promptParts.push(args[i]);
   }
@@ -1352,7 +1356,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
     for (const task of results.musicTasks) await pollMusic(baseUrl, headers, task.taskId);
   } else {
     // Default: fire-and-forget + poll
-    const { runId } = await submitRun(baseUrl, headers, projectId, finalPrompt, { videoModel, preferredModel });
+    const { runId } = await submitRun(baseUrl, headers, projectId, finalPrompt, { videoModel, videoResolution, preferredModel });
     if (background) {
       // Just print runId and exit
       if (jsonOutput) {
@@ -1519,7 +1523,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
 
   } else if (sub === 'create') {
     const images = [];
-    let script = '', duration = undefined, aspectRatio = undefined, videoModel = undefined, wait = false;
+    let script = '', duration = undefined, aspectRatio = undefined, videoModel = undefined, videoResolution = undefined, wait = false;
     let video = null, keepOriginalSound = false;
     for (let i = 2; i < args.length; i++) {
       if (args[i] === '--image' && args[i + 1]) images.push(args[++i]);
@@ -1529,6 +1533,8 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
       else if (args[i] === '--duration' && args[i + 1]) duration = Number(args[++i]);
       else if (args[i] === '--aspect' && args[i + 1]) aspectRatio = args[++i];
       else if (args[i] === '--model' && args[i + 1]) videoModel = args[++i];
+      else if (args[i] === '--video-resolution' && args[i + 1]) videoResolution = args[++i];
+      else if (args[i] === '--resolution' && args[i + 1]) videoResolution = args[++i];
       else if (args[i] === '--keep-original-sound') keepOriginalSound = true;
       else if (args[i] === '--project') {
         console.error('Usage: video create no longer supports --project. Use: makaron chat --project <id> --video <file|url> "your request"');
@@ -1537,7 +1543,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
       else if (args[i] === '--wait') wait = true;
     }
     if ((!images.length && !video) || !script) {
-      console.error('Usage: makaron video create --script "..." (--image <url> | --video <public-url>) [--duration 10] [--aspect 9:16] [--model kling|seedance] [--keep-original-sound]');
+      console.error('Usage: makaron video create --script "..." (--image <url> | --video <public-url>) [--duration 10] [--aspect 9:16] [--model seedance-fast|seedance|kling|grok] [--video-resolution auto|480p|720p|1080p|4k] [--keep-original-sound]');
       process.exit(1);
     }
 
@@ -1548,15 +1554,15 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
 
     let videoUrl = isHttpUrl(video) ? video : null;
     let inputVideoMeta = null;
-    const selectedVideoModel = videoModel || 'kling';
+    const selectedVideoModel = videoModel || 'seedance-fast';
     if (videoUrl) {
-      process.stderr.write(`📹 Assuming public video URL already matches provider reference limits. Seedance requires ≤${MAX_VIDEO_PROVIDER_REFERENCE_DURATION}s, ≤50MB, sides 300-6000px, frame pixels 409,600-${MAX_VIDEO_FRAME_PIXELS}; Kling requires ≤200MB and ≤2K.\n`);
+      process.stderr.write(`📹 Assuming public video URL already matches provider reference limits. Seedance requires ≤${MAX_VIDEO_PROVIDER_REFERENCE_DURATION}s, ≤50MB, sides 300-6000px, frame pixels 409,600-${MAX_VIDEO_FRAME_PIXELS}; Kling requires ≤200MB and ≤2K. Grok does not support video references.\n`);
     }
     if (video && !videoUrl) {
       const valid = validateVideoFile(video, {
         maxDuration: MAX_VIDEO_PROVIDER_REFERENCE_DURATION,
         durationTolerance: MAX_VIDEO_PROVIDER_REFERENCE_DURATION_TOLERANCE,
-        ...(selectedVideoModel === 'seedance' ? {
+        ...(selectedVideoModel === 'seedance' || selectedVideoModel === 'seedance-fast' ? {
           minFramePixels: SEEDANCE_MIN_VIDEO_FRAME_PIXELS,
           minSide: SEEDANCE_MIN_VIDEO_SIDE,
           maxSide: SEEDANCE_MAX_VIDEO_SIDE,
@@ -1574,12 +1580,11 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
     // Standalone MCP tool (no project timeline write)
     process.stderr.write('🎬 Submitting video...\n');
     const vArgs = videoUrl
-      ? { videoUrl, editPrompt: script, images, videoModel: selectedVideoModel, referType: selectedVideoModel === 'seedance' ? 'feature' : 'base' }
-      : { script, images };
+      ? { videoUrl, editPrompt: script, images, videoModel: selectedVideoModel, videoResolution, referType: (selectedVideoModel === 'seedance' || selectedVideoModel === 'seedance-fast') ? 'feature' : 'base' }
+      : { script, images, videoModel: selectedVideoModel, videoResolution };
     const effectiveDuration = duration || (inputVideoMeta?.duration ? Math.min(MAX_VIDEO_PROVIDER_REFERENCE_DURATION, Math.round(inputVideoMeta.duration)) : undefined);
     if (effectiveDuration) vArgs.duration = effectiveDuration;
     if (aspectRatio) vArgs.aspectRatio = aspectRatio;
-    if (videoModel && !videoUrl) vArgs.videoModel = videoModel;
     if (keepOriginalSound && videoUrl) vArgs.keepOriginalSound = true;
     const result = await callMcpTool(baseUrl, headers, videoUrl ? 'makaron_edit_video' : 'makaron_create_video', vArgs);
     const text = result?.content?.find(c => c.type === 'text')?.text;
@@ -1625,7 +1630,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
     console.log(`Video commands:
   video script --image <file> [--image <file>] "direction"   Write video script
   video create --script "..." --image <url> [--duration 10]  Submit video task
-  video create --script "..." --video <public-url> [--model kling|seedance]  Edit a video (standalone)
+  video create --script "..." --video <public-url> [--model seedance-fast|seedance|kling]  Edit a video (standalone; Grok does not support video refs)
   video status <taskId>                                      Check video status
   video status --snapshot <snapshotId> [--wait]              Check v2 video snapshot
 `);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.9.0",
+  "version": "0.10.0",
   "description": "Talk to Makaron Agent from the terminal — create projects, edit images, generate videos",
   "type": "module",
   "scripts": {

package/skills/makaron/SKILL.md

@@ -212,8 +212,8 @@ npx makaron-cli analyze --video input.mp4 "describe the key actions and pacing"
 npx makaron-cli video create --script "Shot 1 (5s): <<<image_1>>> ..." --image https://...jpg --duration 5 --model kling
 
 # 3b. Edit a video from a local file or public URL
-npx makaron-cli video create --script "make it funny" --video input.mp4 --duration 5 --model seedance
-npx makaron-cli video create --script "make it warmer and cinematic" --video https://example.com/input.mp4 --duration 5 --model seedance
+npx makaron-cli video create --script "make it funny" --video input.mp4 --duration 5 --model seedance-fast
+npx makaron-cli video create --script "make it warmer and cinematic" --video https://example.com/input.mp4 --duration 5 --model seedance --video-resolution 1080p
 
 # 4. Check status
 npx makaron-cli video status <taskId>
@@ -225,9 +225,9 @@ npx makaron-cli video status <taskId>
 npx makaron-cli chat --project <id|auto> --video input.mp4 -b "make it funny"
 ```
 
-Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to 7), `--video <file|url>`, `--duration <seconds>`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`. SeeDance accepts integer output duration 4-15s (default 5s); Kling supports 5-15s.
+Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to 7), `--video <file|url>`, `--duration <seconds>`, `--aspect 9:16|16:9|1:1`, `--model seedance-fast|seedance|kling|grok`, `--video-resolution auto|480p|720p|1080p|4k`. Default model is `seedance-fast`. SeeDance accepts integer output duration 4-15s (default 5s); Kling supports 5-15s; Grok 1.5 supports 1-15s single-image-to-video only. For `--model grok`, forced `--aspect` is ignored to avoid xAI stretching the source image; pad/create the image at the target shape first or use another model.
 
-Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance --video` uses the Seedance video-reference path and requires target <=15s, <=50MB, width/height 300-6000px, aspect ratio 0.4-2.5, and frame pixels 409,600-2,086,876. Tiny metadata padding up to 15.5s is accepted and output duration is clamped to 15s.
+Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance-fast --video` or `--model seedance --video` uses the SeeDance video-reference path and requires target <=15s, <=50MB, width/height 300-6000px, aspect ratio 0.4-2.5, and frame pixels 409,600-2,086,876. Tiny metadata padding up to 15.5s is accepted and output duration is clamped to 15s. Grok does not support video references.
 
 ### `music` — Music generation
 
@@ -339,7 +339,7 @@ send_message "All done!"
 - One project = one conversation thread. All history is preserved.
 - One run at a time per project. New message interrupts previous run.
 - Multi-image: `create --image a.jpg --image b.jpg` or `chat --image ref.jpg`.
-- Videos take 2-5 minutes to render. Use `responses get <runId> --wait --json` for the default customer-service path.
+- Most videos take 3-5 minutes; Grok is usually around 30-40 seconds. Use `responses get <runId> --wait --json` for the default customer-service path.
 - Music takes ~60 seconds. Appears in output when done.
 - Images are typically ready in 15-30 seconds.
 - stdout is always machine-readable JSON/text. Human-friendly logs go to stderr.