Explore
playgroundai / playground-v2-1024px-aesthetic
Playground v2 is a diffusion-based text-to-image generative model trained from scratch by the research team at Playground
lucataco / magic-animate
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
nateraw / video-llava
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
01-ai / yi-34b-chat
The Yi series models are large language models trained from scratch by developers at 01.AI.
stability-ai / stable-video-diffusion
SVD is a research-only image to video model
meta / llama-2-70b-chat
A 70 billion parameter language model from Meta, fine tuned for chat completions
Collections
3D models
Models that generate 3D objects, scenes, radiance fields, textures and multi-views.
alaradirik/dreamgaussian , jd7h/zero123plusplus , adirik/wonder3d , adirik/mvdream , adirik/mvdream-multi-view ...
Audio generation
Models to generate and modify audio
meta/musicgen , riffusion/riffusion , suno-ai/bark , afiaka87/tortoise-tts , allenhung1025/looptest ...
ControlNet
Control diffusion models
jagilley/controlnet-scribble , jagilley/controlnet-hough , jagilley/controlnet-canny , jagilley/controlnet-depth2img , jagilley/controlnet-hed ...
Diffusion models
Image and video generation models trained with diffusion processes
stability-ai/stable-diffusion , cjwbw/anything-v3-better-vae , cjwbw/anything-v4.0 , cjwbw/waifu-diffusion , tommoore515/material_stable_diffusion ...
Embedding models
Models that generate embeddings from inputs
andreasjansson/clip-features , replicate/all-mpnet-base-v2 , daanelson/imagebind , nateraw/bge-large-en-v1.5 , nateraw/jina-embeddings-v2-base-en ...
Image editing
Tools for manipulating images.
tencentarc/gfpgan , sczhou/codeformer , rossjillian/controlnet , cjwbw/rembg , andreasjansson/stable-diffusion-inpainting ...
Image restoration
Models that improve or restore images by deblurring, colorization, and removing noise
tencentarc/gfpgan , jingyunliang/swinir , microsoft/bringing-old-photos-back-to-life , megvii-research/nafnet , google-research/maxim ...
Image to text
Models that generate text prompts and captions from images
salesforce/blip , andreasjansson/blip-2 , methexis-inc/img2prompt , yorickvp/llava-13b , rmokady/clip_prefix_caption ...
Language models
Models that can understand and generate text
meta/llama-2-70b-chat , meta/llama-2-13b-chat , meta/llama-2-7b-chat , replicate/dolly-v2-12b , mistralai/mistral-7b-instruct-v0.1 ...
Language models with support for grammars and jsonschema
Language models that support grammar-based decoding as well as jsonschema constraints.
andreasjansson/codellama-7b-instruct-gguf , andreasjansson/llama-2-13b-chat-gguf , andreasjansson/llama-2-70b-chat-gguf , andreasjansson/llama-2-13b-gguf , andreasjansson/wizardcoder-python-34b-v1-gguf ...
ML makeovers
Models that let you change facial features
orpatashnik/styleclip , yuval-alaluf/sam , wty-ustc/hairclip , rinongal/stylegan-nada , mchong6/jojogan ...
SDXL fine-tunes
Some of our favorite SDXL fine-tunes.
fofr/sdxl-emoji , fofr/sdxl-barbie , pwntus/sdxl-gta-v , fofr/sdxl-2004 , fofr/sdxl-tron ...
Streaming language models
Language models that support streaming responses. See https://replicate.com/docs/streaming
meta/llama-2-70b-chat , meta/llama-2-13b-chat , meta/llama-2-7b-chat , yorickvp/llava-13b , fofr/prompt-classifier ...
Style transfer
Models that take a content image and a style reference to produce a new image
huage001/adaattn , ptran1203/pytorch-animegan , paper11667/clipstyler , sanzgiri/cartoonify_video , jiupinjia/stylized-neural-painting-oil ...
Super resolution
Upscaling models that create high-quality images from low-quality images
nightmareai/real-esrgan , jingyunliang/swinir , mv-lab/swin2sr , cjwbw/real-esrgan , cjwbw/rudalle-sr ...
T2I-Adapter
T2I-Adapter models to modify images
alaradirik/t2i-adapter-sdxl-depth-midas , alaradirik/t2i-adapter-sdxl-lineart , alaradirik/t2i-adapter-sdxl-canny , alaradirik/t2i-adapter-sdxl-sketch , cjwbw/t2i-adapter ...
Text to image
Models that generate images from text prompts
stability-ai/stable-diffusion , pixray/text2image , cjwbw/waifu-diffusion , kuprel/min-dalle , laion-ai/erlich ...
Trainable language models
Language models that you can fine-tune using Replicate's training API.
meta/llama-2-70b-chat , meta/llama-2-13b-chat , meta/llama-2-7b-chat , meta/llama-2-7b , meta/llama-2-70b ...
Videos
Models that create and edit videos
deforum/deforum_stable_diffusion , anotherjesse/zeroscope-v2-xl , lucataco/animate-diff , andreasjansson/stable-diffusion-animation , cjwbw/damo-text-to-video ...
Vision models
Multimodal large language models with vision capabilities like object detection and optical character recognition (OCR)
yorickvp/llava-13b , daanelson/minigpt-4 , cjwbw/internlm-xcomposer , joehoover/mplug-owl , lucataco/qwen-vl-chat ...
Popular models
A text-to-image generative AI model that creates beautiful images
A latent text-to-image diffusion model capable of generating photo-realistic images given any text input
Practical face restoration algorithm for *old photos* or *AI-generated faces*
A 7 billion parameter language model from Meta, fine tuned for chat completions
Visual instruction tuning towards large language and vision models with GPT-4 level capabilities
Latest models
Inspired by the vibrant and imaginative style of Ukrainian folk artist Maria Prymachenko, this AI model specializes in creating whimsical and colorful artworks that reflect the essence of traditional folklore and nature themes.
MistralAI's new 8x7B Mixture of Experts (MoE) base model for text generation
MusicGen stereo fine-tuned on Pansori Epic Chant, a Korean folk music with the text token “Korean traditional folk music, pansori”
Fine-tune MusicGen small, medium and melody models. Also stereo models available.
Convert scanned or electronic documents to markdown, very very very fast
An attempt to render Teenage Mutant Ninja Turtles: Mutant Mayhem-like images
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
Playground v2 is a diffusion-based text-to-image generative model trained from scratch. Try out all 3 models here
Kosmos-G: Generating Images in Context with Multimodal Large Language Models
A ~7B parameter language model from Deepseek for SOTA repository level code completion
Source: Pclanglais/MonadGPT ✦ Quant: TheBloke/MonadGPT-AWQ ✦ What would have happened if ChatGPT was invented in the 17th century?
Playground v2 is a diffusion-based text-to-image generative model trained from scratch by the research team at Playground
Source: fblgit/una-cybertron-7b-v2-bf16 ✦ Quant: TheBloke/una-cybertron-7B-v2-AWQ ✦ A 7B MistralAI based model, best on it's series. Trained on SFT, DPO and UNA (Unified Neural Alignment) on multiple datasets
Inference SDXL with cog including multiple models in 1 instance support.
Translate audio while keeping the original style, pronunciation and tone of your original audio.
Convert your videos to DensePose and use it with MagicAnimate
Add a watermark to your videos using the power of Replicate brought to you from your friends at FullJourney.AI
GoogleAI: Style Aligned Image Generation via Shared Attention
Remix the music into another styles with MusicGen Chord
https://www.photoaistudio.com. Take a picture of your face and instantly get any profile picture you want. Only 1 photo, no training needed.
A fine-tuned SDXL LoRA trained on Georgia O'keeffe art