/technology
year old news >mfw Today's Resource news 11/05/2026 >NitroFusion2: Bringing Adversarial Loss to the Text Stream of Multimodal Diffusion Transformers https://chendaryen.github.io/NitroFusion2.github.ioβ§ >UniRestorer++: Scalable Universal Image Restoration with Multi-Granularity Degradation Modeling https://github.com/mrluin/UniRestorer_plusplusβ§ >ChatR Labs Qwen-Image-2.1 Uncensored Omni β Quantized https://huggingface.co/chatrlabs/Qwen-Image-2.1-Uncensored-Omni-Quantizedβ§ >VideoColorMatch: Auto-Fix Color Drift from V2V Generations https://github.com/pftq/VideoColorMatchβ§ >Pyramid-JiT: Training a Text-to-Image Model for $21K https://huggingface.co/Linum-AI/pjit-21kβ§ https://github.com/PedroMarinhoDev/ComfyUI-PJiTβ§ >Vimoo-1.0-Lite-ComfyUI https://huggingface.co/Vimoo-AI/Vimoo-1.0-Lite-ComfyUIβ§ >NanoKV: High-Ratio KV Cache Compression for Autoregressive Video Generation https://jiacheng-lu03.github.io/NanoKVβ§ >FrameScout: Scouting Query-Relevant Frames for Long Video Understanding https://github.com/Hubert-1102/FrameScoutβ§ >LayerShop 0.20: Prompt Enhancement, Batch Rendering & Styles https://github.com/SlavomirDurej/layershop/releases/tag/layershop-v0.20.1-preview.1β§ 11/04/2026 >TaoMate-HD: Progressive-Resolution Autoregressive Audio-Video Generation https://taoliveaigc.github.io/TaoMate-HDβ§ >AuroraIMG2-100M: 100.6M-parameter flow-matching diffusion transformer and a 44.9M-parameter text encoder https://huggingface.co/AuroraAI-Research/AuroraIMG2-100Mβ§ >Kandinsky S2V 1.0 - 2B and 21B models https://kandinskyavatar.github.ioβ§ >BluePixel-Turbo: Native 4K instruction-based image editing in 4 steps https://huggingface.co/openvivo/BluePixel-Turboβ§ >Viggle Remake: Remake any video. Just ask https://huggingface.co/Viggle/Viggle-Remakeβ§ >History Forcing: Distilling History-Dependent Continuations for Long-Horizon Video World Models https://ziplab.co/History-Forcing-Project-Pageβ§β± 2dβ© 1
Common! Turkeys are expensive!!β± 2dβ©