Category: Deep Learning

In this article, we cover the explanation of the Hunyuan3D 2.0 technical report and create a Runpod Docker Image for the same for smoother execution of image-to-3D workflows. ...

In this article we carry out optimizations for the image-to-3D pipeline in terms of VRAM usage, multi-object generation from prompts, and improved UI. The pipeline uses Qwen3-VL, BiRefNet, and Hunyuan3D models. ...

In this article, we cover image-to-texture for 3D meshes using Hunyuan3D, Qwen3-VL, and BiRefNet models ...

In this article we create a simple, yet robust pipeline for image to 3D mesh generation with detection grounding using Qwen3-VL, BiRefNet, and Hunyuan3D 2.0 model. ...

In this article, we convert the DINOv3 model for semantic segmentation and train it on the Pascal VOC segmentation dataset along with analysis of the results and running inference on images and videos. ...