← Back to Skills Marketplace
Tomoviee Reference to Image
by
wondershare-boop
· GitHub ↗
· v1.0.2
· MIT-0
321
Downloads
0
Stars
1
Active Installs
3
Versions
Install in OpenClaw
/install tomoviee-reference-to-image
Description
Generate images from a reference image using Tomoviee Image-to-Image API (`tm_reference_img2img`) through Wondershare OpenAPI gateway (`https://openapi.wonde...
Usage Guidance
This package appears to be what it claims: a Tomoviee image-to-image client that calls openapi.wondershare.cc. Before using it, consider: (1) You'll need to supply app_key/app_secret at runtime — do not paste highly privileged/production secrets unless you trust the vendor and gateway. (2) Avoid providing sensitive reference images if you do not want them sent to a third-party service. (3) Be careful with the optional 'callback' parameter — if you pass a callback URL the remote service may POST generated results (or data) to that URL; use only endpoints you control. (4) The repository contains all client code; if you want extra assurance, review the small Python files yourself (they only use requests and base64). (5) Test with non-sensitive data first and prefer short-lived/test credentials where possible.
Capability Analysis
Type: OpenClaw Skill
Name: tomoviee-reference-to-image
Version: 1.0.2
The skill bundle provides a standard Python client and documentation for interacting with the Tomoviee Image-to-Image API via the Wondershare OpenAPI gateway (openapi.wondershare.cc). The implementation in scripts/tomoviee_img2img_client.py and scripts/generate_auth_token.py follows expected patterns for API authentication and task polling without any evidence of data exfiltration, malicious execution, or obfuscation.
Capability Assessment
Purpose & Capability
Name/description match the included client code and docs. The Python client targets the declared endpoints (openapi.wondershare.cc) and implements the tm_reference_img2img workflow; no unrelated cloud providers, binaries, or secret-scoped env vars are requested.
Instruction Scope
SKILL.md and code stay within the image-to-image task. Two notes: (1) the client accepts a callback URL and will pass it to the remote API, which may cause the remote service to POST results to an arbitrary endpoint — exercise caution when supplying callbacks; (2) references/prompt_guide.md includes broader video/audio prompt guidance beyond strict image-to-image scope (harmless documentation but extra content).
Install Mechanism
No automated install script or remote binary downloads. The repo only lists a single dependency (requests) in requirements.txt and recommends 'pip install -r requirements.txt'. All code is included in the package (no fetch-from-unknown-URL behavior).
Credentials
The skill does not declare required env vars or primary credentials. Credentials (app_key/app_secret) are supplied at runtime to the client and used only to build a Basic auth header in memory; there are no extraneous credential requests or access to system config paths.
Persistence & Privilege
always:false and disable-model-invocation left default; the skill does not request persistent system-wide changes or modify other skills. The code does not write credentials to disk and has no self-elevating install steps.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install tomoviee-reference-to-image - After installation, invoke the skill by name or use
/tomoviee-reference-to-image - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
- Renamed skill to "tomoviee-reference-to-image" and updated descriptions to clarify support for image-to-image editing, style transfer, and subject-preserving transformations.
- Added explicit documentation on endpoint provenance and credential handling for improved transparency and security.
- Introduced new Python client location (`scripts/tomoviee_img2img_client.py`) and added a compatibility shim for the previous client path.
- Expanded and clarified API usage examples, parameter requirements, and async workflow steps.
- Added/updated references to bundled resources and external API documentation.
v1.0.1
- Updated external resource links to use the tomoviee.ai domain instead of tomoviee.cn.
- No other changes were made.
v1.0.0
- Initial release of tomoviee-img2img.
- Supports generating new images based on a reference image with user-specified modifications.
- Provides Python client and example scripts for authentication and API use.
- Allows control over image size, batch output, and transformation type.
- Includes status tracking for async operations.
Metadata
Frequently Asked Questions
What is Tomoviee Reference to Image?
Generate images from a reference image using Tomoviee Image-to-Image API (`tm_reference_img2img`) through Wondershare OpenAPI gateway (`https://openapi.wonde... It is an AI Agent Skill for Claude Code / OpenClaw, with 321 downloads so far.
How do I install Tomoviee Reference to Image?
Run "/install tomoviee-reference-to-image" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Tomoviee Reference to Image free?
Yes, Tomoviee Reference to Image is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Tomoviee Reference to Image support?
Tomoviee Reference to Image is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Tomoviee Reference to Image?
It is built and maintained by wondershare-boop (@wondershare-boop); the current version is v1.0.2.
More Skills