FLUX 3 Image Klein, MOSS-Image & More: Weekly Roundup
Another busy week in open weights. Black Forest Labs dropped a tiny FLUX 3, a new Chinese lab shipped a model that takes layout as […]
How to Use FLUX.3 Klein GGUF Workflow in ComfyUI
FLUX.3 Klein brings fast, high-quality image generation to local AI workflows. In this tutorial, we’ll look at how to use the FLUX.3 Klein Distilled GGUF […]
AI Image & Video Model News Roundup – October 10, 2026
The open-weights world kept moving this week. Below are the most notable open-source image and video model releases, fine-tunes, and ComfyUI tools from October 6 […]
Comfy Agent Is Here: Build ComfyUI Workflows with AI
ComfyUI has become one of the most powerful tools for running AI image and video models locally, but that flexibility comes with a cost: workflows […]
MiniMax H3 Video VAE Gets Up to 2.2x Faster in ComfyUI
ComfyUI has released a major performance improvement for the MiniMax H3 video VAE, making video encoding up to 2.2 times faster and decoding up to […]
How to Use Qwen-Image 2.1 GGUF in ComfyUI
Qwen-Image 2.1 has arrived, bringing a new 7B image-generation component, improved image editing, native transparency support, and support for up to 10 reference images. Qwen […]
FastH3 V2: 8-Step MiniMax H3 Video Generation in ComfyUI
If you have been using MiniMax H3 for AI video generation, there is a new open-weight model worth checking out. FastH3 V2, released by the […]
10Eros-Max: The New MiniMax H3 Model
A new experimental model called 10Eros-Max is pushing MiniMax H3 in an unusual direction. Rather than training a conventional fine-tune from scratch, the project experiments […]
FastH3 Preview: MiniMax H3 Video Generation Up to 14× Faster
If you have been following open-source AI video generation, you probably already know about MiniMax H3. It is one of the more interesting open-weight video […]
How to Use Turbo LoRA with MiniMax H3 GGUF in ComfyUI
MiniMax H3 is an impressive video generation model, but its large model size can make local generation time-consuming, especially when running it through a quantized […]