IMA AI Creative Content Generator#

⚠️ MANDATORY: You MUST read("SKILL-DETAIL.md") (full file — do NOT pass limit parameter) before your first content generation call. It contains the full API payload structure, error translation tables, upload flow, and UX protocol that this summary omits. Skipping it causes parameter errors and poor user experience.

Capabilities#

All-in-one AI content generator across four media types:

MediaModelsContent Creation Use CasesImageSeeDream 4.5, Midjourney, Nano Banana 2/ProAd creatives, social media graphics, product photos, postersVideoWan 2.6, Kling O1/2.6, Veo 3.1, Sora 2 Pro, Hailuo 2.3/2.0, Pixverse, SeeDance, Vidu, Ima SevioPromo videos, short videos, marketing clips, product demosMusicSuno sonic v5, DouBao BGM/SongAd jingles, background music, social media audioTTSseed-tts-2.0Voiceovers, narration, ad audio

Model ID Reference (CRITICAL)#

Use exact model_id. Do NOT infer from friendly names.

Image Models#

Namemodel_idCostSeeDream 4.5 🌟doubao-seedream-4.55 ptsMidjourney 🎨midjourney8-10 ptsNano Banana2 💚gemini-3.1-flash-image4-13 ptsNano Banana Progemini-3-pro-image10-18 pts

Video Models#

Namemodel_id (t2v / i2v)CostWan 2.6 🔥wan2.6-t2v / wan2.6-i2v25-120 ptsKling O1kling-video-o148-120 ptsKling 2.6kling-v2-680+ ptsHailuo 2.3MiniMax-Hailuo-2.332+ ptsHailuo 2.0MiniMax-Hailuo-025+ ptsVeo 3.1veo-3.1-generate-preview70-330 ptsSora 2 Prosora-2-pro122+ ptsPixverse V5.5pixverse12-48 ptsSeeDance 1.5 Prodoubao-seedance-1.5-pro20+ ptsVidu Q2viduq2 / viduq2-pro5-70 ptsIMA Video Proima-provariesIMA Video Pro Fastima-pro-fastvaries

Aliases: 万/Wan→ wan2.6-* · 可灵/Kling→ kling-video-o1 · 海螺/Hailuo→ MiniMax-Hailuo-2.3 · Veo→ veo-3.1-generate-preview

Music & TTS Models#

Namemodel_idCostSuno sonic v5sonic25 ptsDouBao BGMGenBGM30 ptsDouBao SongGenSong30 ptsseed-tts-2.0seed-tts-2.0query product list

Media Type Routing#

Determine media type first, then choose task_type:

User keywordsTypetask_type画/图/image/poster/thumbnail/ad graphicimagetext_to_image, image_to_image视频/video/promo/short/宣传片/clipvideotext_to_video, image_to_video, first_last_frame_to_video, reference_image_to_video音乐/BGM/music/jingle/歌musictext_to_music语音/TTS/voiceover/narration/配音speechtext_to_speech

For multi-media (e.g. promo video + BGM), read ima-knowledge-ai/references/workflow-design.md first.

Video Modes#

Intenttask_typeText only → videotext_to_videoImage as first frameimage_to_videoImage as style referencereference_image_to_videoTwo images (start+end)first_last_frame_to_video

Visual consistency: For "same character" / "series" / "multi-shot" — use image_to_video or reference_image_to_video with previous result as reference. Never use text_to_video for continuity.

Knowledge Base (if ima-knowledge-ai installed)#

Read before generating: workflow-design.md (multi-media), visual-consistency.md (character continuity), video-modes.md (mode differences), model-selection.md (cost/quality).

Default Models#

TaskDefaultmodel_idCosttext_to_imageSeeDream 4.5doubao-seedream-4.55 ptstext_to_videoWan 2.6wan2.6-t2v25 ptsimage_to_videoWan 2.6wan2.6-i2v25 ptsfirst_last_frameKling O1kling-video-o148 ptstext_to_musicSunosonic25 pts

Script Usage#

bash

# AI image generator — ad/social media content creation
python3 {baseDir}/scripts/ima_create.py \
  --api-key $IMA_API_KEY --task-type text_to_image \
  --model-id doubao-seedream-4.5 --prompt "product photo" --output-json

# AI video generator — promo/marketing video content
python3 {baseDir}/scripts/ima_create.py \
  --api-key $IMA_API_KEY --task-type text_to_video \
  --model-id wan2.6-t2v --prompt "product promo, cinematic" --output-json

# AI music generator — ad jingle/marketing audio
python3 {baseDir}/scripts/ima_create.py \
  --api-key $IMA_API_KEY --task-type text_to_music \
  --model-id sonic --prompt "upbeat corporate BGM" --output-json

# TTS — voiceover for content creation
python3 {baseDir}/scripts/ima_create.py \
  --api-key $IMA_API_KEY --task-type text_to_speech \
  --prompt "Welcome to our product" --output-json

UX Protocol (Brief)#

1. Acknowledge: Short reply ("好的！🎨")
2. Pre-gen: Model, time estimate, cost via message tool
3. Progress: Every 15-60s: "⏳ [P]%" (cap 95%)
4. Success: Send media=url + link text
5. Failure: Natural language + suggest alternatives
6. Done: No further action

Never expose: script names, API endpoints, attribute_id, technical params.

User Preferences#

Storage: ~/.openclaw/memory/ima_prefs.json

• Save on explicit: "用XXX" / "默认用XXX" / "always use XXX"
• Clear on: "推荐一个" / "自动选择" / "用最好的"
• Never save auto-selected models

Core Flow#

1. GET /open/v1/product/list?category=<task_type> → attribute_id, credit, form_config
2. [Image tasks] Upload local files → get CDN URL
3. POST /open/v1/tasks/create → task_id
4. POST /open/v1/tasks/detail → poll until resource_status==1

MANDATORY: Always query product list first. Missing attribute_id → task fails.

Environment#

Base URL: https://api.imastudio.com Headers: Authorization: Bearer $IMA_API_KEY · x-app-source: ima_skills · x_app_language: en

---

⚠️ REMINDER: read("SKILL-DETAIL.md") (full file, no limit) is required before generating content. This summary covers routing and model selection — SKILL-DETAIL.md has complete API payloads, error handling, upload flow, and parameter details needed for correct execution.