Liquid AI's LFM2.5 uses a hybrid of short-range convolutions and attention, achieving edge optimization without SSMs. This article covers the architecture, benchmarks, and community use cases.
ByteDance’s Seedance 2.0 has been released on Dreamina. From the perspective of someone who has been using Wan 2.x and ComfyUI locally, I considered how the "ease" differs between local and cloud-based video generation services.
A technical overview of Qwen3‑TTS from Alibaba’s Qwen team: one‑line pip install, 3‑second voice cloning, natural‑language voice design, and support for 10 languages including Japanese. Apache 2.0 licensed.
Technical details of UltraFlux-v1, a model that pushes FLUX.1-dev into native 4K generation. It covers the differences from Z-Image and FLUX.2 Klein, its RoPE extensions and VAE improvements, and practical caveats.
A technical walkthrough of Alibaba's Qwen3-Omni-30B-A3B. An omni-modal model that activates only 3B out of 30B and responds with speech from text/image/audio/video inputs. The article organizes the Thinker–Talker architecture, benchmarks, and the overall Qwen3 MoE family.
A technical look at ByteDance's UI-TARS-1.5-7B, which beats OpenAI CUA and Claude 3.7 by a wide margin at identifying GUI elements from screenshots, and can run locally with a desktop app.
Technical overview of Alibaba’s Qwen3-Coder-Next. An ultra-efficient MoE with 80B parameters but only 3B activated, runs even on a single RTX 4090. Brings 70%+ SWE-Bench performance to local use.
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 between the 'UI UX Pro Max Skill' for AI coding assistants such as Claude Code and the UI/UX improvement articles I wrote earlier. Which works better: automatic inference or explicit human intent?
AnimeGamer, developed by Tencent ARC Lab, generates anime-style videos while tracking game-state transitions. It takes a fundamentally different approach from general-purpose video generation models.
MOVA-720p from the OpenMOSS team is an open-source model that generates video and audio in a single pass. This article covers how it differs from closed models like Vidu Q3 and what its architecture looks like.
