“Runway just dropped a surprise AI image generation model called Frames — and the outputs are absolutely indistinguishable from reality. Just days after the impressive video expansion tool launch, Runway is now cooking with a new image model.
MMGenBench: Evaluating the Limits of LMMs from the Text-to-Image Generation Perspective
[2411.17106v1] PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution
“9th highest scored ICLR 2025 paper 8,8,8,10. Worth noting all reviewers increased their scores by 2 after rebuttals tldr: they introduce a bunch of architectural changes to a diffusion transformer, getting 100x speed improvements with no real quality impacts
“Excited to share our latest paper: Quark – Real-time, high-resolution, and generalized neural view synthesis! 🚀 🎥 1080p @ 30fps 🌍 Generalizes across diverse scenes & datasets 🏆 Achieves real-time quality rivaling even offline methods 🔗 Project page:
lehduong/OneDiffusion
hey-it-s-me/CoRPLE: An implementation of Contourlet Residual for Prompt Learning Enhanced Infrared Image Super-Resolution(CoRPLE)
[2411.13975v1] Transforming Static Images Using Generative Models for Video Salient Object Detection
[2411.13842v1] Detecting Human Artifacts from Text-to-Image Models
“QwenVL-Flux is ABSURDLY cool ⚡️ It’s kind of like an IP Adapter, with QwenVL as the image encoder, adding multiple high quality features: – Image Variation 🎨 – Image Blending 🔄 – Style Transfer 🎯 Kudos to @kuer5ord for training it! ▶️ Play at
“🎨 Excited to announce that Qwen2VL-Flux demo is now ready for testing! This is a lightweight variation of the full model, perfect for quick image transformations with optional text guidance.
“📷 @argilla_io Dataset Drop – Open Image Preferences @bfl_ml Flux Dev VS. @StabilityAI Stable Diffusion Large 3.5 Together with the data-is-better-together community, we’ve worked on an Apache 2.0 licensed image preference dataset based on the @fal imgsys prompts dataset.
[2411.16819] Pathways on the Image Manifold: Image Editing via Video Generation
FLUX
“Flux by @bfl_ml is now the most liked model ever on Hugging Face (out of over 1,000,000 models). Congrats to the team! Also fun to realize that two years ago, there was almost only LLMs on HF and now image, video, audio, biology, chemistry, time-series,… models, datasets and
Leave a Reply