Image to Image enhancer using DemoFusion

Video to OpenPose

MagicAnimate using an OpenPose input video

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

Convert your videos to DensePose and use it with MagicAnimate

GoogleAI: Style Aligned Image Generation via Shared Attention

MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

Given two images depicting a source structure and a target appearance, generate an image merging the structure of one image with the appearance of the other

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

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

DemoFusion: Democratising High-Resolution Image Generation With No 💰

SDXL Image Blending

InterpAny-Clearer: Clearer anytime frame interpolation & Manipulated interpolation

Coqui XTTS-v2: Multilingual Text To Speech Voice Cloning

Controlnet v1.1 - Tile Version

Real-ESRGAN Video Upscaler

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

Research-only StabilityAI's Stable Video Diffusion

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

Animate Your Personalized Text-to-Image Diffusion Models with SDXL and LCM

Text to video diffusion model with variable length frame conditioning for infinite length video

Dreamshaper-7 img2img with LCM LoRA for faster inference

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

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

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

SDXL_Niji_Special Edition

A fine-tuned SDXL-LCM LoRA based on the photos of Zeke

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)

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

POC of SDXL-LCM LoRA combined with Replicate LoRA for 4 second inference times

Latent Consistency Model (LCM): SSD-1B, is a LCM distilled version that reduces the number of inference steps needed to only 2 - 8 steps

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate SDv1.5 images with an image prompt

Implementation of SDXL RealVisXL_V2.0

POC to run inference on Realvisxl2 LoRAs

POC to train Realvisxl2 LoRAs

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

POC to run inference on SSD-1B LoRAs

POC to train SSD-1B LoRAs for cheaper & faster training

Batch mode for Segmind Stable Diffusion Model (SSD-1B) txt2img

Implementation of SDXL RealVisXL_V2.0 img2img

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

Grounding Multimodal Large Language Models to the World

Segmind Stable Diffusion Model (SSD-1B) img2img

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

Implementation of SDXL RealVisXL_V1.0 img2img

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

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

MistralLiteA is a fine-tuned Mistral-7B-v0.1 language model, with enhanced capabilities of processing long context (up to 32K tokens)

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

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

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

Open diffusion model for high-quality video generation

SDXL Inpainting is a latent diffusion model developed by the HF Diffusers team. Keeps input aspect ratio

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.

Using a ComfyUI workflow to run SDXL text2img

Stylized Audio-Driven Single Image Talking Face Animation

SDXL ControlNet - Canny

Mistral-7B-v0.1 is a pretrained generative text model that outperforms Llama 2 13B on all benchmarks

Animate Your Personalized Text-to-Image Diffusion Models

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

Remove background from an image

Implementation of SDXL RealVisXL_V1.0

SDXL ControlNet - Depth

microsoft/phi-1.5 was trained using the same data sources as phi-1, augmented with a new data source that consists of various NLP synthetic texts

CLIP Interrogator (for faster inference)

360 Panorama SDXL image with inpainted wrapping seam

Robust face restoration algorithm for old photos/AI-generated faces - (A40 GPU)

An SDXL fine-tune based on blueprints

Turn any image into a video

Empowering Code Large Language Models with Evol-Instruct

IDEFICS 80b Quantized

IDEFICS 9b Quantized

Realistic Vision V5 with OpenPose

SDXL fine tune on Spider-Gwen style

Realistic Vision v5.0 with VAE

SDXL ControlNet - OpenPose

Realistic Vision v5.0 Inpainting

Realistic Vision v5.0 Image 2 Image

Implementation of Realistic Vision v5.1 with VAE

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

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

2.7B param open source chat model trained on Glaive’s synthetic data generation platform

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

Stability AI's FreeWilly2

Meta's Llama 2 70b Chat - GPTQ

Meta's Llama 2 13b Chat - GPTQ

Meta's Llama 2 7b Chat - GPTQ

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

RiversHaveWings Stable Diffusion Upscaler

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

A working wsrglow model

Image Variations with Stable Diffusion

Realistic Vision V4.0

Realistic Vision V3.0 with VAE

sahil2801/replit-code-instruct-glaive

replit/replit-code-v1-3b

Salesforce/xgen-7b-8k-base

lmsys/vicuna-33b-v1.3

lmsys/vicuna-13b-v1.3

lmsys/vicuna-7b-v1.3

Salesforce/codegen2-1B

mosaicml/mpt-30b-chat in 8bit

bigcode/tiny_starcoder_py

WizardLM/WizardCoder-15B-V1.0

WizardLM/WizardCoder-15B-V1.0 in 4bit

Shiba stable diffusion model