#comfyui

Local text to textured GLB on an AMD Strix Halo iGPU (gfx1151): FLUX.2 klein, a Vulkan-only TRELLIS.2 engine, and humanoid auto-rigging with SkinTokens on ROCm. No Blender, no CUDA.

A simple studio to use agent

Predictive GPU memory framework for AI inference workflows

huggingface_hub, but for CivitAI — inspect and download models/LoRAs from the CLI or as a Python library

Hardened Marinara media bridge for Hermes-managed image generation and managed FLUX 3 video

Local generative-AI as Claude Code plugins for NVIDIA DGX Spark — FLUX.2 images & Hunyuan3D image-to-3D via ComfyUI, with gated S3/CloudFront downloads (Terraform).