I want to…

Restore images

Models that improve or restore images by deblurring, colorization, and removing noise

Upscale images

Upscaling models that create high-quality images from low-quality images

Train a language model

Language models that you can fine-tune using Replicate's training API.

Make 3D stuff

Models that generate 3D objects, scenes, radiance fields, textures and multi-views.

Latest models

Updated 223 runs

A text-to-image generative AI model that creates beautiful images

Updated 51.5M runs

✍️✨Prompts to auto-magically relights your images

Updated 2.1K runs

Replicate version from the work of Shanglin Li et al. called "ZONE: Zero-Shot Instruction-Guided Local Editing"

Updated 24 runs

🖼️✨Background images + prompts to auto-magically relights your images (+normal maps🗺️)

Updated 54 runs

Run any ComfyUI workflow. Guide: https://github.com/fofr/cog-comfyui

Updated 228.1K runs

Super fast clothing segmentation and masking with erosion and dilation capability.

Updated 50 runs

RealVisXL v3 fine-tuned on 80s cyberpunk images

Updated 105 runs

A tiny model for testing out Cog

Updated 62 runs

Updated 16 runs

SDXL-Lightning by ByteDance: a fast text-to-image model that makes high-quality images in 4 steps

Updated 56.9M runs

This is an ML model to segment hairs in pictures.

Updated 42 runs

Generate Seragam Olahraga using AI Diffusion

Updated 109 runs

Segment foreground objects with high resolution and matting, using InSPyReNet

Updated 93 runs

controlnet-depth interior remodelling, keeps windows and ceilings

Updated 37 runs

Updated 16 runs

Updated to OpenVoice v2: Versatile Instant Voice Cloning

Updated 10.7K runs

Updated 4.5K runs

viⓍTTS vixTTS là mô hình tạo sinh giọng nói cho phép bạn sao chép giọng nói sang các ngôn ngữ khác nhau chỉ bằng cách sử dụng một đoạn âm thanh nhanh dài 6 giây

Updated 168 runs

Hermes-2 Θ (Theta) is the first experimental merged model released by Nous Research, in collaboration with Charles Goddard at Arcee, the team behind MergeKit.

Updated 231 runs

Three models in one Cog: Absolute Reality v1.8.1, DreamShaper v8 and Meina V4

Updated 478 runs

Source: gradientai/Llama-3-8B-Instruct-Gradient-4194k ✦ Quant: solidrust/Llama-3-8B-Instruct-Gradient-4194k-AWQ ✦ Extending LLama-3 8B's context length from 8k to 4194K

Updated 21 runs

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

Updated 838.9K runs

📖 PuLID: Pure and Lightning ID Customization via Contrastive Alignment

Updated 26.6K runs

modèle pour faire des images de femme cohérentes

Updated 398 runs

High resolution image Upscaler and Enhancer. Use at ClarityAI.co. A free Magnific alternative. Twitter/X: @philz1337x

Updated 1.6M runs

Updated 141 runs

Face Restoration

Updated 1.9K runs

An example model created from cli

Updated 12 runs

小米 su7 lora测试

Updated 38 runs

PaliGemma 3B, an open VLM by Google, pre-trained with 224*224 input images and 128 token input/output text sequences

Updated 143 runs

A model which generates text in response to an input image and prompt.

Updated 1.3M runs

Generate image with transparent background

Updated 406 runs

Yi-1.5 is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples

Updated 24 runs

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view LRMs

Updated 156 runs

Blip 3 / XGen-MM, Answers questions about images ({blip3,xgen-mm}-phi3-mini-base-r-v1)

Updated 125 runs

A model trained on picture of liminal spaces

Updated 40 runs

A model generated based on a dataset of Eurovision singers

Updated 47 runs

Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant.

Updated 59 runs

return CLIP features for the dfn5b-clip-vit-h-14-384, current highest average perf. in openclip models leaderboard.

Updated 59 runs

Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant.

Updated 380 runs

Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant.

Updated 216 runs

Updated 509 runs

Updated 4.4K runs

Implementation of the RemBG library

Updated 199 runs

BLIP3 is a series of foundational Large Multimodal Models (LMMs) developed by Salesforce AI Research

Updated 206 runs

Transcribe audios using OpenAI's Whisper with stabilizing timestamps by stable-ts python package.

Updated 27 runs

Updated 13 runs

Use a face to make images. Uses SDXL fine-tuned checkpoints.

Updated 3K runs