Description

Use when the user needs image generation or image transformation through the IMA Open API, including text-to-image, image-to-image, style transfer, or refere...

README (SKILL.md)

IMA Image AI

Name: IMA AI Image Generator & Photo Generator — Poster, Thumbnail, Logo, Art, Illustration, Product & Social Media Graphic Design
Author: allenfancy-gan

When To Use

Use this repository when the user wants an image output:

text-to-image
image-to-image
style transfer
continuity via reference image

This repo is image-only. Do not route video generation, audio generation, or non-image tasks here.

Gateway Contract

New-machine bootstrap entrypoint: python3 scripts/ima_runtime_setup.py
Environment/self-check entrypoint: python3 scripts/ima_runtime_doctor.py
The official CLI entrypoint is python3 scripts/ima_runtime_cli.py ....
Always query the live product list before task creation so attribute_id, credit, model_version, and defaults come from the current catalog.
Return remote HTTPS image URLs; do not download results into local attachments for the user.
Route requests through the image capability so text_to_image and image_to_image are classified before execution.
If --model-id is omitted, the runtime uses the recommended default model for that task type.
Auto-selected defaults are operational fallbacks, not persisted user preferences.

Quick Start

Minimal path:
1. python3 scripts/ima_runtime_setup.py --install
2. export IMA_API_KEY="ima_your_key_here"
3. python3 scripts/ima_runtime_cli.py --task-type text_to_image --prompt "a cinematic mountain sunset" --output-json
Use python3 scripts/ima_runtime_doctor.py --output-json when setup passes but runtime or catalog access still fails.

Operator References

README.md covers first-use paths and canonical entry commands.
references/shared/catalog-aware-selection.md defines the formal live-catalog-aware model-selection contract.
references/operations/troubleshooting.md covers common failure recovery.
capabilities/image/references/parameter-tuning.md covers size, aspect_ratio, and n usage.
capabilities/image/references/scenarios.md covers prompt-only and reference-image examples.

Read Order

references/README.md
references/gateway/entry-and-routing.md
references/gateway/workflow-confirmation.md
references/shared/model-selection-policy.md
references/shared/catalog-aware-selection.md
references/shared/error-policy.md
references/shared/security-and-network.md
references/operations/troubleshooting.md
capabilities/image/CAPABILITY.md
capabilities/image/references/parameter-tuning.md
capabilities/image/references/scenarios.md

Boundary

references/gateway/* covers entry, routing, and clarification seams.
references/shared/* covers rules reused across the runtime.
capabilities/image/* owns image-specific behavior.
_meta.json and clawhub.json are metadata inputs, not the primary narrative docs.

Usage Guidance

This skill appears internally consistent for communicating with the IMA image API. Before installing: (1) Verify the API key scope and use a scoped/test key for initial testing (the key is sent to api.imastudio.com and imapi.liveme.com as documented). (2) Inspect scripts/shared/client.py (not fully shown here) if you want to confirm exact network endpoints and that the API key is not logged or written to disk — logs are stored at ~/.openclaw/logs/ima_skills/ and preferences at ~/.openclaw/memory/ima_prefs.json. (3) Be aware the setup script may run pip install to pull 'requests' when --install is used. (4) There is a minor inconsistency in branding/hostnames in metadata (imaclaw.ai vs imastudio.com); if you depend on the vendor identity, confirm the legitimate homepage and API endpoints before putting production credentials into the skill. (5) If you want to limit risk, keep the API key scoped and revoke/regenerate it after testing.

Capability Analysis

Type: OpenClaw Skill Name: ima-image-ai Version: 1.0.14 The IMA Image Generator skill bundle is a legitimate tool for interacting with the IMA Studio API for image generation and transformation. It includes well-structured Python scripts for setup, diagnostics, and CLI execution, with clear documentation in SKILL.md and SECURITY.md regarding its use of the IMA_API_KEY and network communication with api.imastudio.com and imapi.liveme.com. No evidence of malicious intent, data exfiltration, or unauthorized execution was found; all behaviors, including local file uploads and preference persistence in ~/.openclaw/, are aligned with the stated purpose.

Capability Tags

requires-sensitive-credentials

Capability Assessment

✓ Purpose & Capability

Name/description request text-to-image and image-to-image workflows and the skill only requires python3 + IMA_API_KEY and the 'requests' package. Those requirements align with a runtime that calls an external image API and uploads local images when needed.

✓ Instruction Scope

SKILL.md and the included scripts limit behavior to catalog/model selection, task creation, optional local-image upload, and returning remote HTTPS image URLs. The repo documents optional cross-skill reads (~/.openclaw/skills/ima-knowledge-ai/references/*) and the declared instruction scope matches the code paths shown (doctor, setup, CLI, client).

✓ Install Mechanism

No custom install spec; the repo is instruction/code-only. The only install action is an optional pip install -r requirements.txt invoked by the included setup script (uses subprocess to run pip). No arbitrary third-party binary downloads or extract-from-URL steps are present in the provided files.

✓ Credentials

Only one required environment variable (IMA_API_KEY) is declared and documented; SKILL.md and SECURITY.md state the key is sent to api.imastudio.com and to imapi.liveme.com for local uploads. No other unrelated credentials are requested.

✓ Persistence & Privilege

The skill does not request 'always: true'. It writes only to user-scoped paths (~/.openclaw/memory/ima_prefs.json and ~/.openclaw/logs/ima_skills/) and optionally reads a specific cross-skill reference path if present. It does not modify other skills or system-wide settings in the visible code.

Version History

v1.0.14

- Added compiled Python bytecode files (`.pyc`) for core runtime, adapters, capabilities, and shared modules. - Bundled prebuilt cache for CLI, setup, doctor, image capability execution, and shared utilities. - No changes to documentation or configuration files. - No functional code updates; this version introduces only precompiled assets for runtime modules.

v1.0.13

- Overhauled codebase with new modular structure and image-aware capability layer. - Added 48 files, including detailed operator and API documentation, scenario guides, catalog-aware model selection, and troubleshooting references. - Introduced new runtime scripts and CLI with setup, doctor, catalog, and task routing flow. - Removed legacy scripts and changelog. - All model selection and image runtime logic now routes through live product catalog for real-time defaults and consistency. - Documentation rewritten for clarity, first-use onboarding, and advanced configuration.

v1.0.12

No user-facing changes in this release. - Version bump only; no content or code updates detected.

v1.0.11

No file changes detected. No user-visible changes in this version.

v1.0.10

No detectable file changes or feature updates in this version. - No functional or documentation changes from previous release. - Version number incremented only; all behaviors and instructions unchanged.

v1.0.9

Version 1.0.9 - Added SKILL-DETAIL.md for detailed API documentation, usage, and guidance. - No changes to code; this is a documentation supplement release. - All functionality and core instructions remain unchanged.

v1.0.8

- Added new !keywords.txt file to the project. - Enhanced discoverability with expanded keywords and synonyms, covering model names and generative tasks (e.g., seedream, nano banana, t2i, i2i, AI art, MJ). - No functional or interface changes; skill usage remains the same.

v1.0.7

- Added a SECURITY.md file to establish security policies and reporting guidelines. - Updated documentation to clarify that ima-knowledge-ai is now an optional enhancement; the skill works standalone but will utilize ima-knowledge-ai if available. - Expanded environment variable, credential, and persistence notes in the SKILL.md to document required API keys and local data handling. - No code or functionality changes to image generation logic.

v1.0.6

IMA Image AI 1.0.6 Changelog - Added .gitignore file to the repository. - No user-facing changes to code or documentation in this version.

v1.0.5

ima-image-ai 1.0.5 - Added initial CHANGELOG_CLAWHUB.md for official changelog tracking. - Added clawhub.json for Clawhub integration and metadata.

v1.0.4

No changes detected in this version (1.0.4). - No file changes or updates were made from the previous release. - Skill version remains unchanged; all features and behaviors remain the same.

v1.0.3

IMA Studio Image Generation v1.0.3 - Refactored documentation to rely on an external knowledge base ("ima-knowledge-ai") for workflow, visual consistency, and best practices; now highlights correct model/parameter selection even if ima-knowledge-ai is not installed. - Added detailed user input parsing tables to ensure consistent extraction of task type, model, and parameters from user language, including normalization rules for supported models and sizes. - Updated model list and instructions for intelligent automatic model selection, covering SeeDream 4.5, Midjourney, Nano Banana 2, and Nano Banana Pro. - Streamlined and clarified the user experience protocol for messaging platforms. Kept acknowledgment, progress, and result delivery unchanged. - Removed redundant/instructional files: CHANGELOG_CLAWHUB.md, INSTALL.md, README.md, SECURITY.md, and clawhub.json. This version is a major documentation/UX update with no core functionality change.

v1.0.2

IMA Image AI 1.0.2 → 1.0.3 - Added mandatory pre-check for visual consistency: Must read ima-knowledge-ai/visual-consistency.md and check if image-to-image is needed for "series"/"same character" tasks before generating. - Updated SKILL.md with step-by-step instructions to enforce knowledge base guidance and correct usage for repeated/series/character prompts. - Improved skill description to warn users to consult ima-knowledge-ai for best practices. - No changes to user-facing generation protocol or model options.

v1.0.1

- Removed script file scripts/ima_image_create.py. - Added compiled Python cache file scripts/__pycache__/ima_logger.cpython-314.pyc. - No functional or user-facing changes documented in SKILL.md or description. - Version number in SKILL.md remains at 1.0.2 (no update needed).

v1.0.0

IMA Studio Image Generation 1.0.2 introduces detailed user experience guidance and default model selection rules. - Added clear, step-by-step IM/Discord user experience protocol with acknowledgment, progress, and results. - Default model: SeeDream 4.5 (latest and most popular), with options for premium, budget, and Midjourney models; clear recommendation logic. - New: Always send initial friendly acknowledgment reply before any update. - Enhanced captions: Show original image URL for easy sharing. - Transparent cost, timing, and status communication—users see credits, estimated/real time, and model used. - Improved error handling: No technical language; all errors shown in plain language with retry suggestions.

Metadata

Slug ima-image-ai

Version 1.0.14

License MIT-0

All-time Installs 1

Active Installs 1

Total Versions 15

Frequently Asked Questions

What is IMA AI Image Generator & Photo Generator — Poster, Thumbnail, Logo, Art, Illustration, Product & Social Media Graphic Design?

Use when the user needs image generation or image transformation through the IMA Open API, including text-to-image, image-to-image, style transfer, or refere... It is an AI Agent Skill for Claude Code / OpenClaw, with 976 downloads so far.

How do I install IMA AI Image Generator & Photo Generator — Poster, Thumbnail, Logo, Art, Illustration, Product & Social Media Graphic Design?

Run "/install ima-image-ai" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is IMA AI Image Generator & Photo Generator — Poster, Thumbnail, Logo, Art, Illustration, Product & Social Media Graphic Design free?

Yes, IMA AI Image Generator & Photo Generator — Poster, Thumbnail, Logo, Art, Illustration, Product & Social Media Graphic Design is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does IMA AI Image Generator & Photo Generator — Poster, Thumbnail, Logo, Art, Illustration, Product & Social Media Graphic Design support?

IMA AI Image Generator & Photo Generator — Poster, Thumbnail, Logo, Art, Illustration, Product & Social Media Graphic Design is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created IMA AI Image Generator & Photo Generator — Poster, Thumbnail, Logo, Art, Illustration, Product & Social Media Graphic Design?

It is built and maintained by allenfancy-gan (@allenfancy-gan); the current version is v1.0.14.

More Skills

IMA AI Image Generator & Photo Generator — Poster, Thumbnail, Logo, Art, Illustration, Product & Social Media Graphic Design