Explore

I want to…

Make videos with Wan2.1

Generate videos with Wan2.1, the fastest and highest quality open-source video generation model.

Restore images

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

Enhance videos

Models that enhance videos with super-resolution, sound effects, motion capture and other useful production effects.

Detect objects

Models that detect or segment objects in images and videos.

Make 3D stuff

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

Use FLUX fine-tunes

Browse the diverse range of fine-tunes the community has custom-trained on Replicate

Control image generation

Guide image generation with more than just text. Use edge detection, depth maps, and sketches to get the results you want.

Latest models

deepseek-ai/deepseek-v3

The leading non-reasoning model, a milestone for open source

Updated 76 runs

As SDXL has better finetunes than SD3.5

Updated 141 runs

Controllable generative AI art

Updated 328 runs

This model generates pose variation of a cartoon character. It preserves the cartoon identity. Use this model to augment training dataset for any cartoon character created through AI. The augmented dataset can be used to train a LoRA model.

Updated 3.6K runs

Best-in-class clothing virtual try on in the wild (non-commercial use only)

Updated 652.3K runs

Easily create video datasets with auto-captioning for Hunyuan-Video LoRA finetuning

Updated 508 runs

0.5B

Updated 8 runs

Updated 51 runs

8B TTS

Updated 10 runs

recraft-ai/recraft-v3

Recraft V3 (code-named red_panda) is a text-to-image model with the ability to generate long texts, and images in a wide list of styles. As of today, it is SOTA in image generation, proven by the Text-to-Image Benchmark by Artificial Analysis

Updated 2.3M runs

recraft-ai/recraft-v3-svg

Recraft V3 SVG (code-named red_panda) is a text-to-image model with the ability to generate high quality SVG images including logotypes, and icons. The model supports a wide list of styles.

Updated 80.4K runs

recraft-ai/recraft-20b-svg

Affordable and fast vector images

Updated 16.8K runs

recraft-ai/recraft-20b

Affordable and fast images

Updated 85.5K runs

Updated 122 runs

The Fish Speech V1.1 model.

Updated 32 runs

Generates MagicaVoxel VOX models, using flux dev + hunyuan3d-2. Can generate high detail and low detail models at varying resolutions.

Updated 93 runs

flux dev

Updated 93K runs

RF-DETR: SOTA Real-Time Object Detection Model

Updated 14 runs

epicrealism-naturalsinfinal-SD1.5-by-epinikion + perfectdeliberate by Desync + More Details by Lykon

Updated 37 runs

Updated 76 runs

Updated 20K runs

Scaling Diffusion Models for High Resolution Textured 3D Assets Generation

Updated 2.5K runs

Updated 39 runs

Updated 2.4K runs

Updated 35 runs

Updated 609 runs

Updated 67 runs

Updated 161 runs

Updated 329 runs

Extract the first or last frame from any video file as a high-quality image

Updated 21 runs

CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs

Updated 128 runs

flux-1.dev

Updated 14 runs

Updated 145 runs

Fish Speech V1.5-SOTA Open Source TTS

Updated 183 runs

A model Flux.1-dev-Controlnet-Upscaler by www.androcoders.in

Updated 42 runs

Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Updated 579 runs

Updated 7.4K runs

Orpheus 3B - high quality, emotive Text to Speech

Updated 2.7K runs

Updated 8.7K runs

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

Updated 2.9M runs

kwaivgi/kling-v1.6-pro

Generate 5s and 10s videos in 1080p resolution

Updated 86.3K runs

CosyVoice2-0.5B-Scalable Streaming Speech Synthesis with Large Language Models

Updated 584 runs

A model Flux.1-dev-Controlnet-Upscaler by www.androcoders.in

Updated 378 runs

Realistic Inpainting with ControlNET (M-LSD + SEG)

Updated 403.7K runs

Hunyuan3D-2mv is finetuned from Hunyuan3D-2 to support multiview controlled shape generation.

Updated 579 runs

LatentSync: generate high-quality lip sync animations

Updated 20K runs

detect correct orientation of images

Updated 17 runs

Hyper FLUX 8-step by ByteDance

Updated 8.2M runs

ShieldGemma 2 is a model trained on Gemma 3's 4B IT checkpoint for image safety classification across key categories that takes in images and outputs safety labels per policy.

Updated 7 runs