/technology
>mfw Resource news 06/11/2025 >HunyuanCustom inference code and model weights released https://github.com/Tencent-Hunyuan/HunyuanCustom#-newsβ§ >Towards Vision-Language-Garment Models For Web Knowledge Garment Understanding and Generation https://georgenakayama.github.io/AIpparelβ§ >WanGP 5.4 w/ Hunyuan Video Avatar Support (Runs in 10GB) https://github.com/deepbeepmeep/Wan2GP#may-28-2025-wangp-v54β§ >MARBLE: Material Recomposition and Blending in CLIP-Space https://marblecontrol.github.ioβ§ >Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels https://genintel.github.io/DIY-SCβ§ >Invisible Backdoor Triggers in Image Editing Model via Deep Watermarking https://github.com/aiiu-lab/BackdoorImageEditingβ§ >ContentV: Efficient Training of Video Generation Models with Limited Compute https://contentv.github.ioβ§ >AliTok: Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model https://github.com/ali-vilab/alitokβ§ >MokA: Multimodal Low-Rank Adaptation for MLLMs https://gewu-lab.github.io/MokAβ§ >FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing https://flowdirector-edit.github.ioβ§ >ComfyUI-Copilot: An Intelligent Assistant for Automated Workflow Development https://github.com/AIDC-AI/ComfyUI-Copilotβ§ >ComfyUI Blog: Subgraphs Are Coming to ComfyUI https://blog.comfy.org/p/subgraphs-are-coming-to-comfyuiβ§ >Diffusion Domain Teacher: Diffusion Guided Domain Adaptive Object Detector https://github.com/heboyong/Diffusion-Domain-Teacherβ§ >RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectors https://github.com/pralab/RAIDβ§ >Image Editing As Programs with Diffusion Models https://github.com/YujiaHu1109/IEAPβ§ >Vocabulary-free few-shot learning for Vision-Language Models https://github.com/MaxZanella/vocabulary-free-FSLβ§ >RefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model on Referring Expressions http://refedit.vercel.appβ§β± 2dβ© 4
Thank you bro!β± 2dβ©
+ 3