Explore

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

controlnet-depth interior remodelling, keeps windows and ceilings

Updated 92 runs

Inference SDXL with cog including multiple models in 1 instance support.

Updated 6.4K runs

araby.ai oneshot faceswap

Updated 70 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 267 runs

SDXL based text-to-image model applying Distribution Matching Distillation, supporting zero-shot identity generation in 2-5s. https://ai-visionboard.com

Updated 1.9M runs

Fast sdxl with higher quality

Updated 240 runs

Guided Text to Speech Generator

Updated 41 runs

make a music

Updated 127 runs

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

Updated 250.8K runs

Super fast clothing (and face) segmentation and masking with erosion and dilation capability.

Updated 903 runs

for test

Updated 8 runs

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

Updated 52.2M runs

A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Updated 28 runs

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

Updated 11K runs

Recreate images with Emojis

Updated 63 runs

This is phi-3-vision model , cost by time ,have fun~

Updated 26 runs

Updated 4.5K runs

Convert story to StableDiffusion prompts format

Updated 30 runs

openai whisper model on A100 hardware

Updated 36 runs

SDXL Fine tuned on sketchnote style images. Prompt Prefix: a sketchnote photo of TOK

Updated 50 runs

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

Updated 1.8M runs

SDXL fine tuned for sketch output style

Updated 106 runs

klkl\]\

Updated 710 runs

Image tagger fine-tuned on WaifuDiffusion w/ (SwinV2, SwinV2, ConvNext, and ViT)

Updated 12 runs

Updated 1.7K runs

✍️✨Prompts to auto-magically relights your images

Updated 2.7K runs

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

Updated 54 runs

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

Updated 164 runs

RealVisXL v3 fine-tuned on 80s cyberpunk images

Updated 160 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 71.5M runs

This is an ML model to segment hairs in pictures.

Updated 51 runs

Generate Seragam Olahraga using AI Diffusion

Updated 124 runs

Segment foreground objects with high resolution and matting, using InSPyReNet

Updated 133 runs

Updated 16 runs

Updated to OpenVoice v2: Versatile Instant Voice Cloning

Updated 11.9K runs

Updated 4.6K 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 732 runs

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

Updated 5.9K 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 26 runs

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

Updated 839.1K runs

📖 PuLID: Pure and Lightning ID Customization via Contrastive Alignment

Updated 30.2K runs

modèle pour faire des images de femme cohérentes

Updated 591 runs

Updated 233 runs

Face Restoration

Updated 2K runs

An example model created from cli

Updated 12 runs

小米 su7 lora测试

Updated 41 runs

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

Updated 192 runs