Stable Diffusion NCNN
This server provides CPU-based Stable Diffusion image generation capabilities through the ncnn neural network inference framework, enabling offline text-to-image generation without GPU requirements. Built in C++ as a stdio-based MCP server, it exposes a text-to-image tool that accepts prompts and generates PNG images with configurable parameters including dimensions, inference steps, seed control, and multiple output formats. The implementation leverages ncnn's lightweight inference engine to run stable diffusion models entirely on CPU, making it valuable for environments where GPU access is limited or unavailable, edge computing scenarios, and developers who need local image generation without cloud dependencies.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- media
- Source
- PulseMCP
- Repository
- github.com/chentyjpm/ncnn_llm-mcp-sdimggen
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Stable Diffusion NCNN from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.