acihandemir·Aug 19WAN NASIL VİDEO ÜRETİYOR?Önceki bölümlerde difüzyon modellerinin nasıl görsel ürettiğinden bahsetniştim.Basitçe akış aşağıdaki gibi ilerliyordu:
Jun Nishimura·Mar 16Pico-MoEDiT: How Class-Routed MoE Gave a Tiny DiT a 43% Quality Boost for Emoji Generation“One change cut our loss by 43% — and it wasn’t scaling up the model, the data, or the compute. It was giving each emoji category its own…
Jun Nishimura·Mar 11Why Stable Diffusion 3 Switched to Rectified Flow: A Visual ExplorerBuilding a tiny Diffusion Transformer from scratch in JAX to see why Stable Diffusion 3, Flux, and Sora all switched to Rectified Flow.
Jun Nishimura·Feb 16The Architecture Behind Every State-of-the-Art Image Generator: DiT + Rectified Flow, ExplainedThe two ideas behind Stable Diffusion 3, Flux, and Sora — how they work, and what makes them tick.
ComfyAI·Jan 12NeurIPS25 oral DiT training speed up new SOTA: REGA recent collaboration between Nankai University and Harvard University has produced a standout NeurIPS 2025 Oral paper that might just…
RODISON ROBERTO SANTOS·Jul 7, 2025Schrijf dit nietSchrijf dit niet Dit wordt niet geschreven Het zal oren verwonden Heilige zal scheuren Kuise ogen Zal goede vernietigen Gedachten…
Raffaella Aghemo·May 19, 2025Intelligenza Artificiale, bot e la “Dead Internet Theory”a cura di Raffaella Aghemo
InGoPenAIbyArXiv In-depth Analysis·Mar 4, 2025RelaCtrl, a new version of ControlNet under the DiT architecture…RelaCtrl, a new ControlNet under the DiT architecture, with parameters reduced by 85% and performance on par with SOTA!
AI2060·Feb 18, 2025SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion TransformersEfficiently generate 4k imagesA response icon1A response icon1
xdit-project·Oct 14, 2024利用xDiT多GPU并行执行CogVideoX文生视频流程最近，PixelDance 和 Meta Movie Gen 的发布引发了广泛关注，文生视频应用因此备受瞩目。这些工具以出色的视频生成质量，令一些自媒体纷纷感叹技术的飞速发展。正如不久前发布的…
