A stylized poster style for text-to-image

Realistic Vision v5.0 with VAE

Change the fps of a video without changing its length or speed

SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution

stylegan3 + clip

Updated to OpenVoice v2: Versatile Instant Voice Cloning

Notus-7b-v1 model

Source: llamas-community/LlamaGuard-7b ✦ Quant: TheBloke/LlamaGuard-7B-AWQ ✦ Llama-Guard is a 7B parameter Llama 2-based input-output safeguard model

Fast image interpolation model

lightweight text-to-speech (TTS) model, trained on 10.5K hours of audio data

SDXL Image Blending

nsdxl

Stable Diffusion 3 with Differential Diffusion inpainting (experimental)

First version of my panorama LoRA (use 1024x512)

Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer

Mama ママ 2.0 Shinsei Galverse Anime-themed text-to-image model

Audio-based Lip Synchronization for Talking Head Video

SDXL LoRA I trained on chihuahua images

ReNoise: Real Image Inversion Through Iterative Noising

High accuracy depth maps from pairs of stereo images