Go ahead and axolotl questions

Pusa: Thousands Timesteps Video Diffusion Model

OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from simple icons to in…

Official repo for CFG-Zero*

This is the project for 'Any2Caption', Interpreting Any Condition to Caption for Controllable Video Generation

RF-DETR is a real-time object detection model architecture developed by Roboflow, SOTA on COCO & designed for fine-tuning.

[CVPR 2025] MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

PyTorch video decoding

Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields

[ARXIV'25] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

PaCMAP: Large-scale Dimension Reduction Technique Preserving Both Global and Local Structure

Official implementation of Inductive Moment Matching

Official implementations for paper: VACE: All-in-One Video Creation and Editing

YOLOE: Real-Time Seeing Anything

[CVPR 2025] Official repo for ART:Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation

Model code for inferencing T5

The ultimate training toolkit for finetuning diffusion models

Di♪♪Rhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion

ConceptAttention: A method for interpreting multi-modal diffusion transformers.

stochastic bfloat16 based optimizer library

MoD Control Tile Upscaler for SDXL Pipeline

NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms

The repo for "Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator"

SpargeAttention: A training-free sparse attention that can accelerate any model inference.

Dear PyGui: A fast and powerful Graphical User Interface Toolkit for Python with minimal dependencies

AssetStudio - Based on the archived Perfare's AssetStudio, I continue Perfare's work to keep AssetStudio up-to-date, with support for new Unity versions and additional improvements.

SliderSpace: Decomposing the Visual Capabilities of Diffusion Models

A demo for the Direct Ascent Synthesis: Hidden Generative Capabilities in Discriminative Models paper (https://arxiv.org/abs/2502.07753)