GB-Power-Market-JJ IMA AI Video Generator

install

source · Clone the upstream repo

git clone https://github.com/GeorgeDoors888/GB-Power-Market-JJ

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/GeorgeDoors888/GB-Power-Market-JJ "$T" && mkdir -p ~/.claude/skills && cp -r "$T/openclaw-skills/skills/allenfancy-gan/ima-video-ai" ~/.claude/skills/georgedoors888-gb-power-market-jj-ima-ai-video-generator && rm -rf "$T"

OpenClaw · Install into ~/.openclaw/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/GeorgeDoors888/GB-Power-Market-JJ "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/openclaw-skills/skills/allenfancy-gan/ima-video-ai" ~/.openclaw/skills/georgedoors888-gb-power-market-jj-ima-ai-video-generator && rm -rf "$T"

manifest: openclaw-skills/skills/allenfancy-gan/ima-video-ai/SKILL.md

source content

IMA Video AI — Video Generator

For complete API documentation, security details, all parameters, error tables, and Python examples, read

SKILL-DETAIL.md

Model ID Reference (CRITICAL)

Use exact model_id for the active task_type (t2v vs i2v differ for some models). Do NOT infer from friendly names.

Friendly Name	model_id (t2v)	model_id (i2v)	Notes
Wan 2.6	`wan2.6-t2v`	`wan2.6-i2v`	⚠️ -t2v / -i2v suffix
IMA Video Pro (Sevio 1.0)	`ima-pro`	`ima-pro`	IMA native quality
IMA Video Pro Fast	`ima-pro-fast`	`ima-pro-fast`	Faster iteration
Kling O1	`kling-video-o1`	`kling-video-o1`	⚠️ video- prefix
Kling 2.6	`kling-v2-6`	`kling-v2-6`	⚠️ v prefix
Hailuo 2.3	`MiniMax-Hailuo-2.3`	`MiniMax-Hailuo-2.3`	⚠️ MiniMax- prefix
Hailuo 2.0	`MiniMax-Hailuo-02`	`MiniMax-Hailuo-02`	⚠️ 02 not 2.0
Vidu Q2	`viduq2`	`viduq2-pro`	⚠️ i2v often -pro
Google Veo 3.1	`veo-3.1-generate-preview`	`veo-3.1-generate-preview`	⚠️ -generate-preview
Sora 2 Pro	`sora-2-pro`	`sora-2-pro`	Content policy strict
Pixverse	`pixverse`	`pixverse`	Version via product list
SeeDance 1.5 Pro	`doubao-seedance-1.5-pro`	`doubao-seedance-1.5-pro`	⚠️ doubao- prefix

Aliases: 万/Wan → Wan 2.6 · 可灵O1 →

kling-video-o1

· 海螺2.3 →

MiniMax-Hailuo-2.3

· Veo →

veo-3.1-generate-preview

· Ima Sevio 1.0 →

ima-pro

· Ima Sevio 1.0-Fast →

ima-pro-fast

Use

--list-models --task-type <text_to_video|image_to_video|...>

when unsure.

Video Modes (task_type)

User intent	task_type
Text only	`text_to_video`
Image becomes frame 1	`image_to_video`
Image is visual reference (not frame 1)	`reference_image_to_video`
Two images: first + last frame	`first_last_frame_to_video`

If ima-knowledge-ai is installed, read

references/video-modes.md

and

visual-consistency.md

when user needs continuity across shots or references a previous image.

Visual Consistency (IMPORTANT)

Text-only generation cannot reliably keep the same character/scene across runs.
For “同一个角色 / 续集 / 分镜”: use image modes with the prior result (or reference image), not
```
text_to_video
```
alone.

Model Selection Priority

User explicit preference (saved in
```
ima_prefs.json
```
only when user clearly picks a model)
ima-knowledge-ai (if installed)
Fallback defaults (see SKILL-DETAIL.md for full table)

Task	Default (fallback)	model_id
text_to_video	Wan 2.6	`wan2.6-t2v`
image_to_video	Wan 2.6	`wan2.6-i2v`
first_last_frame_to_video	Kling O1	`kling-video-o1`
reference_image_to_video	Kling O1	`kling-video-o1`

Script Usage

# Text to video
python3 {baseDir}/scripts/ima_video_create.py \
  --api-key $IMA_API_KEY \
  --task-type text_to_video \
  --model-id wan2.6-t2v \
  --prompt "a puppy runs across a sunny meadow, cinematic" \
  --user-id {user_id} \
  --output-json

# Image to video (URLs or local paths; script uploads locals)
python3 {baseDir}/scripts/ima_video_create.py \
  --api-key $IMA_API_KEY \
  --task-type image_to_video \
  --model-id wan2.6-i2v \
  --prompt "camera slowly zooms in" \
  --input-images https://example.com/photo.jpg \
  --user-id {user_id} \
  --output-json

# First–last frame
python3 {baseDir}/scripts/ima_video_create.py \
  --api-key $IMA_API_KEY \
  --task-type first_last_frame_to_video \
  --model-id kling-video-o1 \
  --prompt "smooth transition" \
  --input-images https://example.com/first.jpg https://example.com/last.jpg \
  --user-id {user_id} \
  --output-json

Sending Results to User

video_url = json_output["url"]
message(action="send", media=video_url, caption="✅ 视频生成成功！\n• 模型：[Name]\n• 耗时：[X]s\n• 积分：[N pts]\n\n🔗 原始链接：[url]")

Never download to a local path for

media

— use the HTTPS URL from the API.

UX Protocol (Brief)

Pre-generation: model name · estimated time range · credits
Progress: poll ~8s; update user every 30–60s; cap % at 95 until done
Success: send
```
media=video_url
```
, then optional text with link for copy/share
Failure: plain-language reason + 1–2 alternate models — never raw API errors. Full error table in SKILL-DETAIL.md.

Never say to users: script names, endpoints,

attribute_id

, internal field names.

Environment

Base URL:

https://api.imastudio.com

Headers:

Authorization: Bearer $IMA_API_KEY

x-app-source: ima_skills

x_app_language: en

Image upload (when needed):

imapi.liveme.com

(same provider; see SKILL-DETAIL.md).

Core Flow

GET /open/v1/product/list?app=ima&platform=web&category=<task_type>

→

attribute_id

credit

model_version

form_config

Image tasks: ensure public HTTPS URLs (script handles local upload)
```
POST /open/v1/tasks/create
```
→
```
task_id
```
```
POST /open/v1/tasks/detail
```
→ poll every 8s, timeout up to ~40 min as documented in detail file

MANDATORY: Always query product list first; wrong or stale

attribute_id

causes create failures.

User Preference Memory

Path:

~/.openclaw/memory/ima_prefs.json

Save when user explicitly chooses a default model; clear when they ask for “推荐 / 自动 / 最好的”. Do not save auto-picked models as preference.

Polling & Timing (summary)

Kind	Poll interval	Typical wait
Most models	8s	~1–6 min
Heavy models (e.g. Kling O1, Sora Pro, Veo)	8s	longer; see SKILL-DETAIL.md table

Sora 2 Pro (brief)

Strict safety: avoid people, celebrities, and IP in prompts; prefer landscapes/abstract/safe subjects — details in SKILL-DETAIL.md.