cuda-kernels
Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers libraries. Supports models like LTX-Video, Stable Diffusion, LLaMA, Mistral, and Qwen. Includes integration with HuggingFace Kernels Hub (get_kernel) for loading pre-compiled kernels. Includes benchmarking scripts to compare kernel performance against baseline implementations.
ai-image-generation
Facilitates creation of visual content using generative AI models including DALL-E, Midjourney prompts, and Stable Diffusion workflows.
diffusion-perf
Deprecated alias (merged into diffusion-kernel).
HF Daily Papers (OpenClaw Skill)
Generate a daily list of trending papers from Hugging Face Papers, filtered into: - Generation (diffusion / video / image / generative) - Efficient (attention / sparse / quant / memory / optimization)
Image Generation MCP Server
MCP server for AI image generation via OpenAI, Stable Diffusion (SD WebUI), or placeholders.