>mfw Resource news

10/26/2025

>Pony V7
https://huggingface.co/purplesmartai/pony-v7-base

>FlashPack: High-throughput tensor loading for PyTorch
https://github.com/fal-ai/flashpack

>LongCat-Video: Text-to-Video, Image-to-Video, and Video-Continuation generation
https://huggingface.co/meituan-longcat/LongCat-Video

>Sora might have a 'pervert' problem on its hands
https://www.businessinsider.com/sora-video-openai-fetish-content-my-face-problem-2025-10

10/24/2025

>Stability AI and EA Partner to Empower Artists, Designers, and Developers to Reimagine Game Development
https://stability.ai/news/stability-ai-and-ea-partner-to-reimagine-game-development

>DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion
https://noamissachar.github.io/DyPE

>EditInfinity: Image Editing with Binary-Quantized Generative Models
https://github.com/yx-chen-ust/EditInfinity

>RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling
https://github.com/Vchitect/RAPO

>HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives
https://holo-cine.github.io

10/23/2025

>next-scene-qwen-image-lora-2509 Version 2
https://huggingface.co/lovis93/next-scene-qwen-image-lora-2509

>ComfyUI-FlashVSR_Ultra_Fast
https://github.com/lihaoyun6/ComfyUI-FlashVSR_Ultra_Fast

>AToken: A Unified Tokenizer for Vision
https://github.com/apple/ml-atoken

>LTX-2 (API Only)
https://website.ltx.video/blog/introducing-ltx-2

10/22/2025

>LightMem: Lightweight and Efficient Memory-Augmented Generation
https://github.com/zjunlp/LightMem

>ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder
https://github.com/VisionXLab/ProCLIP

>Ranking-based Preference Optimization for Diffusion Models from Implicit User Feedback
https://github.com/basiclab/DiffusionDRO

>Beyond Single Models: Mitigating Multimodal Hallucinations via Adaptive Token Ensemble Decoding
https://github.com/jinlin2021/ATED