cjwbw / supir

Remove images background

openai/clip-vit-large-patch14 with Transformers

ZoeDepth: Combining relative and metric depth

high-quality, highly detailed anime style stable-diffusion with better VAE

high-quality, highly detailed anime-style Stable Diffusion models

Anime-themed text-to-image stable diffusion model

Real-ESRGAN: Real-World Blind Super-Resolution

Dream Shaper stable diffusion

Stable Diffusion on Danbooru images

powerful open-source visual language model

Colorization using a Generative Color Prior for Natural Images

Real-ESRGAN super-resolution model from ruDALL-E

Robust Monocular Depth Estimation

high-quality, highly detailed anime style stable-diffusion

sd-v2 with diffusers, test version!

a dreambooth model trained on a diverse set of analog photographs

Generate t-shirt logos with stable-dfffusion

Demucs Music Source Separation

Advanced text-image comprehension and composition based on InternLM

Multi-stage text-to-video generation

Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder

Stylized Audio-Driven Single Image Talking Face Animation

stable-diffusion-v2-inpainting

SeamlessM4T—Massively Multilingual & Multimodal Machine Translation

Detailed, higher-resolution images from Stable Diffusion

stable-diffusion with negative prompts, more scheduler

with large-v2 checkpoint

Background removal model developed by BRIA.AI, trained on a carefully selected dataset and is available as an open-source model for non-commercial use.

VideoCrafter2: Text-to-Video and Image-to-Video Generation and Editing

Unsupervised Night Image Enhancement

Text-to-Image Diffusion Models are Zero-Shot Video Generators

stable-diffusion with v1-5 checkpoint

Tuning-Free Multi-Subject Image Generation with Localized Attention

high-quality highly detailed anime stylized latent diffusion model

mixed stable diffusion model

Adding semantic labels for segment anything

Portraits with stable-diffusion

VQ-Diffusion for Text-to-Image Synthesis

Image Manipulatinon with Diffusion Autoencoders

Generating Conditional 3D Implicit Functions

High-Quality Video Generation with Cascaded Latent Diffusion Models

stable-diffusion models for high quality and detailed anime images

Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild. This is the SUPIR-v0F model and does NOT use LLaVA-13b.

Audio-Driven Synthesis of Photorealistic Portrait Animations

Zero-Shot Speech Editing and Text-to-Speech in the Wild

Pose-Invariant Hairstyle Transfer

Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild. This is the SUPIR-v0Q model and does NOT use LLaVA-13b.

Point-E: A System for Generating 3D Point Clouds from Complex Prompts

A linear estimator on top of clip to predict the aesthetic quality of pictures

Decoding Micromotion in Low-dimensional Latent Spaces from StyleGAN

fine-tuned Stable Diffusion model trained on the game art from Elden Ring

Zero-shot Image-to-Image Translation

Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding

Van Gough on Stable Diffusion via Dreambooth

Finte-tuned Stable Diffusion on high quality 3D images with a futuristic Sci-Fi theme

GTA5 Artwork Diffusion via Dreambooth

Generates pokemon sprites from prompt

generate pixel art sprite sheets from four different angles with Stable-diffusion

face alignment using stylegan-encoding

Highly practical solution for robust monocular depth estimation by training on a combination of 1.5M labeled images and 62M+ unlabeled images

Clip-Guided Diffusion Model for Image Generation

Efficient Pretraining of Text-to-Image Models

text-to-image with latent diffusion

Inpainting using Denoising Diffusion Probabilistic Models

Learning Adapters towards Controllable for Text-to-Image Diffusion Models

End-to-End Document Image Enhancement Transformer

Kandinsky Image Generation with ControlNet Conditioning

Separate Anything You Describe

dreambooth trained on a very diverse dataset ranging from photographs to paintings

Disco Diffusion style on Stable Diffusion via Dreambooth

Efficient Diffusion Model for Image Super-resolution by Residual Shifting

Real-Time High-Resolution Background Matting

Stable Diffusion v2-1-unclip Model

App Icons Generator V1 (DreamBooth Model)

Prompt-to-prompt image editing with cross-attention control

Training-free Controllable Text-to-Video Generation

Added downloadable subtitles for openai/whisper

A Visual Language Model for GUI Agents

herge_style on Stable Diffusion via Dreambooth

Controlling Vision-Language Models for Universal Image Restoration

stable-diffusion-textual-inversion fine-tuned with ugly sonic

Consistent Diffusion Features for Consistent Video Editing

Finetuned Stable-diffusion from Gerry Anderson Supermarionation

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

text-to-image generation

Diffusion Models as Text Painters

Open-source Distilled Stable Diffusion 100% speedup

Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis

Panoptic Scene Graph Generation

High-quality multilingual text-to-speech library

text-to-video generation model

One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale

Tuning-free Higher-Resolution Visual Generation with Diffusion Models

Text-conditional image generation model based on OpenAI's unCLIP

Diffusion Models for Image Morphing

RESEARCH/NON-COMMERCIAL USE ONLY: diffusion-based audio-driven expressive talking head generation

Fine-tuned GPT-J 6B model on the Alpaca dataset

Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation