kalebbroo 

C# client library for SwarmUI API. Provides strongly typed access to generation, model management, and server administration.

Core tensor types, backend abstractions, and shared interfaces for the HartsyInference AI inference engine.

CLIP, T5, Qwen3, and Whisper tokenizers for HartsyInference diffusion and audio pipelines. Ships canonical OpenAI-CLIP / T5-XXL / Qwen3-4B vocabularies as embedded resources so consumers can construct... More information

Model loading for HartsyInference — safetensors, GGUF, model registry, and HuggingFace Hub integration.

Image generation pipelines for HartsyInference — SD1.5, SDXL, Flux, SD3, LoRA, ControlNet, and schedulers.

CPU inference backend for HartsyInference with AVX2/AVX-512/NEON SIMD kernels.

Video generation for HartsyInference — LTX-Video, Wan, temporal attention, and video VAE. (Phase 3 — stub)

Audio inference for HartsyInference — Whisper STT, Kokoro TTS, voice conversion, mel-spectrogram preprocessing, audio codecs, and HuggingFace model caching.

CUDA GPU inference backend for HartsyInference with PTX kernels and cuBLAS integration.

Vulkan compute backend for HartsyInference. Cross-vendor GPU inference (NVIDIA, AMD, Intel, Apple via MoltenVK) via SPIR-V compute shaders and P/Invoke into the Vulkan loader.

Interactive world models for HartsyInference — action-conditioned real-time streaming sessions, camera/Plücker conditioning, FOV memory retrieval, and Matrix-Game pipelines. (Phase 10)

Vision inference for HartsyInference — CLIP embeddings, YOLO detection (planned), SAM segmentation (planned), and face detection (planned).

Meta-package for HartsyInference — a pure C#/.NET AI inference engine for non-LLM modalities (diffusion image generation, speech-to-text, text-to-speech, vision, video, interactive world models). Adds all... More information

Model loading for SharpInference — safetensors, GGUF, model registry, and HuggingFace Hub integration.

Audio inference for SharpInference — Whisper STT, Kokoro TTS, voice conversion, mel-spectrogram preprocessing, audio codecs, and HuggingFace model caching.

3D asset generation for HartsyInference — image/text → mesh and Gaussian-splat. Representation-agnostic foundation (marching cubes, glTF/OBJ/PLY export, 3D sampling) plus model pipelines (Hunyuan3D-2... More information