>mfw Resource news

10/13/2025

>Boosting Multi-modal Keyphrase Prediction with Dynamic Chain-of-Thought in Vision-Language Models
https://github.com/bytedance/DynamicCoT

>Stable Video Infinity: Infinite-Length Video Generation with Error Recycling
https://stable-video-infinity.github.io/homepage

>MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation
https://github.com/sony/mmaudiosep

>Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation
https://kangliao929.github.io/projects/puffin

>Local Dream 2.1.0 with upscalers for NPU models
https://github.com/xororz/local-dream/releases/tag/v2.1.0

>Nvidia’s AI empire: A look at its top startup investments
https://techcrunch.com/2025/10/12/nvidias-ai-empire-a-look-at-its-top-startup-investments

10/12/2025

>Local Dream 2.0 adds embeddings and prompt weights
https://github.com/xororz/local-dream/releases/tag/v2.0.0

>VNCCS - Visual Novel Character Creation Suite V1.1.0
https://github.com/AHEKOT/ComfyUI_VNCCS/releases/tag/1.1.0

>rCM: Score-Regularized Continuous-Time Consistency Model, Diffusion Distillation & Few-Step Video Generation
https://github.com/NVlabs/rcm

>Game over or next level? The generative AI debate in video game creation
https://www.kuow.org/stories/game-over-or-next-level-the-generative-ai-debate-in-video-game-creation

>next-scene-qwen-image-lora-2509: LoRA adapter to generate cinematic image sequences
https://huggingface.co/lovis93/next-scene-qwen-image-lora-2509

>The Transformation Engine: LLM-powered structured prompts and transformations for video generation models
https://github.com/fblissjr/the-transformation-engine

>ComfyUI-Blender Update v3
https://github.com/alexisrolland/ComfyUI-Blender/releases/tag/v3.0.0

10/10/2025

>DreamOmni2: Multimodal Instruction-based Editing and Generation
https://github.com/dvlab-research/DreamOmni2