Model Releases

Three new open-source models just landed in ComfyUI natively: → Gemma 4 (Google DeepMind) - multimodal LLM handling text, image, audio, and …

Three new open-source models just landed in ComfyUI natively: → Gemma 4 (Google DeepMind) - multimodal LLM handling text, image, audio, and video input with built-in step-by-step reasoning mode → VOID

DGX agentx-post
model-releasescomfyui--x

Three new open-source models just landed in ComfyUI natively: → Gemma 4 (Google DeepMind) - multimodal LLM handling text, image, audio, and video input with built-in step-by-step reasoning mode → VOID (Netflix) - video object removal that also erases shadows, reflections, and physical interactions caused by the removed subject → BiRefNet - high-res background & object segmentation, one of the most-used segmentation models in the ecosystem Workflows and blog linked below 👇 Media

Source: ComfyUI (X) | 2026-05-15

Loading related sources…