Browse by category
Pick what you want to do. We'll narrow it down for you — every category is filtered by what your hardware can actually run.
Start with the largest graph
Resolution, frames, extra models, and offload determine fit.
Start with the model family
SD 1.5, SDXL, and Flux have different memory envelopes.
Budget weights plus cache
Context, concurrency, and runtime overhead sit outside the model file.
Category directory
3D & Spatial
Generate meshes, NeRFs, Gaussian splats, and avatars from images or text.
Agent Frameworks
Build autonomous AI agents that reason, plan, and use tools.
AI Video Editing
Upscaling, inpainting, restyle, frame interpolation.
Audio & Speech Generation
Text-to-speech, voice cloning, music & sound effect generation.
Custom Nodes & Extensions
Plugins, custom nodes, and extensions for ComfyUI & friends.
Heavy Image Generation
High-end diffusion models — SDXL, Flux, SD3, Hunyuan.
Heavy Video Generation
Local & cloud video diffusion: Wan, Hunyuan, CogVideoX, LTX.
Local LLM Runners
Run large language models on your own hardware.
Orchestration & APIs
Run pipelines at scale — serverless GPUs, queue managers.
Training & Fine-tuning
LoRA / DreamBooth / full fine-tune toolkits.
Workflow Engines
Nodal & graph-based AI workflow builders.