Resources for DisfluencySpeech

The implementation of the paper "Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention" (NeurIPS`24)

Batched Runge-Kutta Samplers for ComfyUI

From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"

Official repository for "CFG++: manifold-constrained classifier free guidance for diffusion models"

Motion Matching implementation for Unity

[CVPR2024] Official implementation of High-fidelity Person-centric Subject-to-Image Synthesis.

Semantic Consistency Score for measuring the consistency of image generation in diffusion models.

(SIGGRAPH 2024) Official repository for "Taming Diffusion Probabilistic Models for Character Control"

[CVPR'24] DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation

[CVPRW 2024] Official Implementation of "in2IN: Leveraging individual Information to Generate Human INteractions".

Official implementation of "Perturbed-Attention Guidance"

[NeurIPSw'24] This repo is the official implementation of "MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control "

Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.

collection of diffusion model papers categorized by their subareas

Provide large guidance scale correction for Stable Diffusion web UI (AUTOMATIC1111), implementing the paper "Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale"

Official repository of Agent Attention (ECCV2024)

Experimental implementation of CADS for ComfyUI

Blender addons.

The official implementation of HierSpeech++

Concept Sliders for Precise Control of Diffusion Models

Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.

Extension for Stable Diffusion web-ui enables negative prompt in prompt

A Full-Duplex Open-Domain Dialogue Agent with Continuous Turn-Taking Behavior

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

a1111 implementation of https://github.com/ChenyangSi/FreeU

Generating Upper-Body Motion for Real-Time Characters Making their Way through Dynamic Environments - 2022 - SCA

[NeurIPS 2023] MotionGPT: Human Motion as a Foreign Language, a unified motion-language generation model using LLMs