A custom ComfyUI node that adds support for the Qwen 3.5 4B hybrid (Mamba2 + Attention) text encoder for use with the Anima 2B diffusion model. The base Anima 2B ships with a Qwen 3 0.6B text encoder.

"I want to make an MV, but the workflow seems difficult..." Good news for those people. By using the ComfyUI template "LTX 2.3 — Image/Audio to Video," you can generate video clips using just a single ...

This is a 14-billion-parameter video diffusion model running locally. It is not lightweight. Verify your system can handle it before installing. Validated configuration (all benchmarks in this README) ...

ComfyUI is a node-based generative AI application where processes for image generation AI, video generation AI, etc., are connected as "nodes." You place nodes for model loading, prompt processing, ...

RTX GPUs enable fast, private, and unrestricted visual AI generation on personal computers worldwide today. Stable Diffusion and ComfyUI simplify local AI image creation for non-technical users across ...

Click to play. Examples from the recent explosion of celebrity Hunyuan LoRAs from the civit.ai community. At the moment the two most popular ways of generating Hunyuan LoRA models locally are: 1) The ...