camenduru / magictime

MoE-LLaVA

AnimateDiff-Lightning: Cross-Model Diffusion Distillation

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

ControlNet Line Art Anime

TripoSR: Fast 3D Object Reconstruction from a Single Image

Create a video from an image

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

MetaVoice-1B: 1.2B parameter base model trained on 100K hours of speech

Remove background from images using BRIA-RMBG-1.4

Guiding Instruction-based Image Editing via Multimodal Large Language Models

DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation

StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text

APISR: Anime Production Inspired Real-World Anime Super-Resolution

Open Sora Plan Text To Video

one-shot-talking-face-replicate

DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

ZeST: Zero-Shot Material Transfer from a Single Image

Arc2Face: A Foundation Model of Human Faces

Hand Refiner 512x512

AnimateLCM Cartoon3D Model

StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation

Open-Sora is a work-in-progress model.

Visual Style Prompting with Swapping Self-Attention

LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation

MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens

CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model

MagicDance: Realistic Human Dance Video Generation with Motions & Facial Expressions Transfer

GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation

HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach

DUSt3R: Geometric 3D Vision Made Easy

Mixtral-8x22b-v0.1-4bit

IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models

Mixtral-8x22b-v0.1-Instruct-Open-Hermes

ReNoise: Real Image Inversion Through Iterative Noising

Mixtral 8x22b v0.1 Zephyr Orpo 141b A35b v0.1

Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions

EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling

GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

Rethinking Inductive Biases for Surface Normal Estimation

MotionDirector: Motion Customization of Text-to-Video Diffusion Models