WAN 2.2 image-to-video on Windows + RTX 4060 8GB VRAM in ComfyUI. The 5B fp8 model produced rough output across three failed attempts; the 14B Rapid distilled model with --lowvram offloading hit 111 seconds per 2-second clip. Working setup and what to avoid.
Setup notes for running WAI-Illustrious SDXL v16 on ComfyUI with an 8GB RTX 4060 Laptop. 1024x1024 generates in ~15 seconds without --lowvram, and a LoRA still loads. CUDA 12.8 portable build and path gotchas included.
As of February 2026, the Seedance 2.0 API is not yet public. This article summarizes the outlook for ComfyUI integration once the API is released and the preparations to make.
Upscaling images loaded via the Load Image node was producing garbled output. Fixed it by addressing the non-contiguous tensor issue — a one-line patch to comfy/utils.py. Added a 2026-04-29 follow-up after a ComfyUI update wiped the patch and the bug came back, with the upstream PyTorch issue and a recurrence-detection snippet.
A summary of ComfyUI's 'The Complete AI Upscaling Handbook' covering the difference between conservative and creative upscaling, model selection by use case, and benchmarks for both image and video.
Anima is an anime-focused image generation model co-developed by CircleStone Labs and Comfy Org. Built on a new architecture, the preview release draws attention — but how does it actually perform? A look at its strengths, weaknesses, and comparison with existing SDXL-based models.
Published as an official ComfyUI workflow, InfiniteTalk is a lip-sync model specialized in generating mouth animation from audio files. This article covers how it differs from MOVA and Vidu Q3 and what models it requires.
A comparison of the Nunchaku quantized build, VNCCS Pose Studio, and the official 2511 model improvements to find better ways to control pose and camera angle.
A derivative checkpoint of Z-Image Turbo released on ModelScope. It is tuned for skin texture and film-photography-like aesthetics, and can run on an M1 Max with 64GB.
