JSPM

  • ESM via JSPM
  • ES Module Entrypoint
  • Export Map
  • Keywords
  • License
  • Repository URL
  • TypeScript Types
  • README
  • Created
  • Published
  • Downloads 23
  • Score
    100M100P100Q78212F
  • License MIT

IMA Studio CLI - Command-line tool for IMA Studio AI content generation platform

Package Exports

  • imastudio-cli
  • imastudio-cli/src/index.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (imastudio-cli) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

IMA Studio CLI

Command-line tool for IMA Studio — AI content generation platform.

Generate images, videos, music, and speech from the command line. Designed for both human use and AI agent integration.

Install

npm install -g imastudio-cli

Requires Node.js 18+.

Quick Start

# 1. Configure your API key
ima init

# 2. See what you can create
ima list-task-types

# 3. List available models
ima list-models text_to_image

# 4. Generate an image
ima create-task \
  --task-type text_to_image \
  --model-id doubao-seedream-4.5 \
  --prompt "a mountain sunset, photorealistic" \
  --wait

# 5. Check a task
ima task-status <task-id>

Task Types

Task Type Input Output Description
text_to_image prompt image Generate an image from a text prompt.
image_to_image prompt + image(s) image Edit a single image (style transfer, object removal, etc.) or fuse multiple reference images into one.
text_to_video prompt video Generate a video from a text prompt.
image_to_video prompt + image video Generate a video using the input image as the first frame.
first_last_frame_to_video prompt + 2 images video Generate a video that starts with the first image and ends with the second.
reference_image_to_video prompt + image(s) video Generate a video using reference images for visual guidance (characters, style, objects) — not as literal frames.
text_to_music prompt audio Generate instrumental music from a description, or a full song (vocals + music) from lyrics.
text_to_speech text audio Convert text into spoken audio (TTS).

Commands

Command Description
ima init Interactive setup — configure API key
ima list-task-types List supported task types
ima list-models <type> List models for a task type
ima model-info <model-id> Detailed model info (pricing, params)
ima upload <file> Upload a file to IMA CDN
ima create-task Create a generation task
ima task-status <id> Check task status / get results
ima doctor Diagnose environment and connectivity

API Key

Your IMA API key is read from (in priority order):

  1. --api-key CLI flag
  2. IMA_API_KEY environment variable
  3. ~/.imastudio/credentials file

Get your key at imastudio.com.

# Option 1: Interactive setup (recommended)
ima init

# Option 2: Environment variable
export IMA_API_KEY=ima_your_key_here

# Option 3: Per-command
ima list-models text_to_image --api-key ima_your_key_here

Examples

Text to Image

# SeeDream 4.5 (default, 5 pts)
ima create-task \
  --task-type text_to_image \
  --model-id doubao-seedream-4.5 \
  --prompt "cute cat wearing a tiny hat" \
  --wait

# Nano Banana Pro, 4K resolution
ima create-task \
  --task-type text_to_image \
  --model-id gemini-3-pro-image \
  --prompt "product photo of a coffee cup" \
  --size 4K \
  --wait

# 16:9 widescreen
ima create-task \
  --task-type text_to_image \
  --model-id doubao-seedream-4.5 \
  --prompt "panoramic city skyline at dusk" \
  --aspect-ratio 16:9 \
  --wait

Image to Image

# Style transfer
ima create-task \
  --task-type image_to_image \
  --model-id doubao-seedream-4.5 \
  --prompt "turn into oil painting style" \
  --input-images ./photo.jpg \
  --wait

# Using a URL as input
ima create-task \
  --task-type image_to_image \
  --model-id gemini-3-pro-image \
  --prompt "remove background, keep subject" \
  --input-images https://example.com/photo.jpg \
  --wait

JSON Output (for scripts & agents)

# All commands support --json
ima list-models text_to_image --json
ima create-task --task-type text_to_image --model-id doubao-seedream-4.5 --prompt "hello" --wait --json

Upload Files

# Upload an image and get CDN URL
ima upload ./my-photo.jpg
# URL: https://ima-ga.esxscloud.com/...

Agent Integration

This CLI is designed to be the single tool an AI agent needs to interact with IMA Studio. The agent workflow:

ima list-task-types          → discover capabilities
ima list-models <type>       → pick a model
ima model-info <id>          → get pricing/params
ima upload <file>            → upload inputs (if needed)
ima create-task ... --wait   → generate content
ima task-status <id>         → check async results

All commands support --json for machine-readable output. No hardcoded model tables needed — everything is fetched at runtime.

Configuration

~/.imastudio/
├── credentials     # API key (chmod 600)
├── config.json     # User preferences (future)
└── cache/          # Cached product lists (1h TTL)

Available Models (as of 2026-04)

Image Generation

Model ID Cost Notes
SeeDream 4.5 doubao-seedream-4.5 5 pts Default, 4K, aspect ratio support
Nano Banana 2 gemini-3.1-flash-image 4-13 pts Budget option, size tiers
Nano Banana Pro gemini-3-pro-image 10-18 pts Premium, 1K/2K/4K
Midjourney midjourney 8-10 pts Artistic styles

Run ima list-models <type> for the latest — models and pricing update without CLI version changes.

License

MIT