Fresh Cv articles, tutorials, technical notes, and tool updates from StableLearn.
MOSS-VL-Realtime technical introduction and quickstart: OpenMOSS has open-sourced an 11B realtime video understanding model with a 256K context window, timestamped frame input, streaming interaction, proactive silence, and dynamic correction.
Baidu ERNIE-Image: 8B parameter open-source text-to-image AI model achieves SOTA performance. GenEval 0.8856, LongTextBench 0.96+. Superior text rendering, runs on 24GB VRAM, 8-step Turbo mode.
Meet Qwen-Image-Edit-2511, an upgraded Qwen image editing model that reduces drift, boosts character consistency, and ships with integrated LoRA effects. Quick Diffusers code included.
GLM-4.6V free open-source multimodal AI model guide. 106B/9B versions, 128K context, image recognition, OCR, PDF understanding, video analysis.
Z-Image is Alibaba Tongyi's 6B parameter open-source text-to-image model, rivaling closed-source SOTA! 8-step inference with sub-second latency, runs on 16GB VRAM. Supports Chinese & English text rendering, leads in AI Arena human preference evaluation.
Master SAM 3D Objects: Meta's revolutionary single-image 3D reconstruction model. Turn photos into 3D models instantly with Python examples, setup guide, and real applications.
Master SAM3: Meta's revolutionary AI segmentation model with 4M+ concepts. Complete tutorial covering installation, Python examples, text prompts for precise image/video segmentation. Boost your CV projects with this open-vocabulary model guide.
A guide to Microsoft TRELLIS - an open-source 3D generation model for creating high-quality 3D content from images and text, with tutorials on deployment
Explore how STAR leverages text-to-video diffusion models to enhance real-world video super-resolution, including technical principles and practical guidelines
Hallo3 is an open-source portrait animation model by Fudan Vision Lab using Diffusion Transformer Networks to generate realistic talking head videos from photos and audio.
