lucataco / llama-3-vision-alpha

Remove background from an image

Falcons.ai Fine-Tuned Vision Transformer (ViT) for NSFW Image Classification

Implementation of Realistic Vision v5.1 with VAE

FLUX.1-Dev LoRA Explorer

SDXL ControlNet - Canny

SDXL Inpainting by the HF Diffusers team

Juggernaut XL v9

Turn any image into a video

Segmind Stable Diffusion Model (SSD-1B) is a distilled 50% smaller version of SDXL, offering a 60% speedup while maintaining high-quality text-to-image generation capabilities

Hyper FLUX 8-step by ByteDance

CLIP Interrogator for SDXL optimizes text prompts to match a given image

A multimodal LLM-based AI assistant, which is trained with alignment techniques. Qwen-VL-Chat supports more flexible interaction, such as multi-round question answering, and creative capabilities.

FLUX.1-Dev Multi LoRA Explorer

Robust face restoration algorithm for old photos/AI-generated faces

FLUX.1-Schnell LoRA Explorer

Coqui XTTS-v2: Multilingual Text To Speech Voice Cloning

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

😊 Hotshot-XL is an AI text-to-GIF model trained to work alongside Stable Diffusion XL

snowflake-arctic-embed is a suite of text embedding models that focuses on creating high-quality retrieval models optimized for performance

Latent Consistency Model (LCM): SDXL, distills the original model into a version that requires fewer steps (4 to 8 instead of the original 25 to 50)

Monster Labs QrCode ControlNet on top of SD Realistic Vision v5.1

RealvisXL-v2.0 with LCM LoRA - requires fewer steps (4 to 8 instead of the original 40 to 50)

Implementation of SDXL RealVisXL_V2.0

Animate Your Personalized Text-to-Image Diffusion Models

moondream2 is a small vision language model designed to run efficiently on edge devices

Practical face restoration algorithm for *old photos* or *AI-generated faces* (for larger images)

DreamShaper is a general purpose SD model that aims at doing everything well, photos, art, anime, manga. It's designed to match Midjourney and DALL-E.

Realistic Vision v5.0 Image 2 Image

Real-ESRGAN Video Upscaler

A unique fusion that showcases exceptional prompt adherence and semantic understanding, it seems to be a step above base SDXL and a step closer to DALLE-3 in terms of prompt comprehension

CLIP Interrogator (for faster inference)

dreamshaper-xl-lightning is a Stable Diffusion model that has been fine-tuned on SDXL

Phi-3-Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets

Realistic Vision V4.0

SDXL_Niji_Special Edition

PixArt-Alpha 1024px is a transformer-based text-to-image diffusion system trained on text embeddings from T5

MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

Dreamshaper-7 img2img with LCM LoRA for faster inference

AI-driven audio enhancement for your audio files, powered by Resemble AI

Ostris AI-Toolkit for Flux LoRA Training (DEPRECATED. Please use: ostris/flux-dev-lora-trainer)

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

Implementation of SDXL RealVisXL_V1.0

SDXL Image Blending

(Academic and Non-commercial use only) Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization

BakLLaVA-1 is a Mistral 7B base augmented with the LLaVA 1.5 architecture

lmsys/vicuna-13b-v1.3

Mistral-7B-v0.1 fine tuned for chat with the Dolphin dataset (an open-source implementation of Microsoft's Orca)

Real-ESRGAN with optional face correction and adjustable upscale (for larger images)

Realistic Vision v5.0 Inpainting

Gemma2 2b by Google

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate SDXL images with an image prompt

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

SDXL ControlNet - Depth

Realistic Vision v5.0 with VAE

lmsys/vicuna-7b-v1.3

(Research only) IP-Adapter-FaceID can generate various style images conditioned on a face with only text prompts

SDXL ControlNet - OpenPose

Meta's Llama 2 7b Chat - GPTQ

sdxs-512-0.9 can generate high-resolution images in real-time based on prompt texts, trained using score distillation and feature matching

Stylized Audio-Driven Single Image Talking Face Animation

Meta's Llama 2 13b Chat - GPTQ

WizardCoder: Empowering Code Large Language Models with Evol-Instruct

ThinkDiffusionXL is a go-to model capable of amazing photorealism that's also versatile enough to generate high-quality images across a variety of styles and subjects without needing to be a prompting genius

This is wizard-vicuna-13b trained with a subset of the dataset - responses that contained alignment / moralizing were removed

Hyper FLUX 16-step by ByteDance

Mistral-7B-v0.1 fine tuned for chat with the Dolphin dataset (an open-source implementation of Microsoft's Orca)

FalconAIs NSFW detection model, extended for videos

Image-to-video - SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction

InterpAny-Clearer: Clearer anytime frame interpolation & Manipulated interpolation

Segments an audio recording based on who is speaking (on A100)

Latest model in the Qwen family for chatting with video and image models

(Research only) Moondream1 is a vision language model that performs on par with models twice its size

Image to Image enhancer using DemoFusion

Open diffusion model for high-quality video generation

Auto fuse a user's face onto the template image, with a similar appearance to the user

DemoFusion: Democratising High-Resolution Image Generation With No 💰

SDXL lightning mult-controlnet, img2img & inpainting

Ollama Nemotron 70b

Segment Anything 2 (SAM2) by Meta - Automatic mask generation

Implementation of SDXL RealVisXL_V2.0 img2img

Phi-3-Mini-128K-Instruct is a 3.8 billion-parameter, lightweight, state-of-the-art open model trained using the Phi-3 datasets

Stable Diffusion x4 upscaler model

Cog wrapper for Ollama llama3:70b

360 Panorama SDXL image with inpainted wrapping seam

Convert your videos to DensePose and use it with MagicAnimate

Realistic Vision V5 with OpenPose

Realistic Vision V3.0 with VAE

Fuyu-8B is a multi-modal text and image transformer trained by Adept AI

Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data

Controlnet v1.1 - Tile Version

SDXL using DeepCache

nomic-embed-text-v1 is 8192 context length text encoder that surpasses OpenAI text-embedding-ada-002 and text-embedding-3-small performance on short and long context tasks

Playground v2 is a diffusion-based text-to-image generative model trained from scratch. Try out all 3 models here

Segmind Stable Diffusion Model (SSD-1B) img2img

A combination of ip_adapter SDv1.5 and mediapipe-face to inpaint a face

Phi-2 by Microsoft

Implementation of SDXL RealVisXL_V1.0 img2img

Upstage/Llama-2-70B-instruct-v2 - GPTQ

POC to run inference on Realvisxl2 LoRAs

A Flux LoRA trained on watercolor style photos