A quantized 13B parameter language model from NexusFlow for SOTA zero-shot function calling

Take audio from one video and add it to a second video. Good for adding back audio to liveportrait.

SDXL v1.0 - A text-to-image generative AI model that creates beautiful images

amrul-hzz's fine-tuned version of vit-base-patch16-224-in21k for watermark image detection

Hermes-2 Θ (Theta) 70B is the continuation of our experimental merged model released by Nous Research

EpicRealism with all Controlnet Models included

GoogleAI: Style Aligned Image Generation via Shared Attention

face alignment using stylegan-encoding

Synthiola is a synthetic being living in SDXL latent space: https://www.fabianmosele.com/synthiola

Upscale Portrait Images with ControlNet Tile

Feed forward VQGAN-CLIP model

MAT: Mask-Aware Transformer for Large Hole Image Inpainting

SDXL for Embersteel | Andraxus

Implementation of the latest Stable Video Diffusion model in Cog for inference on Replicate

SDXL fine-tuned on characters and objects from Richard Scarry's Busytown

Realistic Vision V3.0 (New)

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

Extended video synthesis model that generates 128 frames

Detailed, higher-resolution images from Stable Diffusion

Kandinsky 2.1 Diffusion Model