Explore

I want to…

Use official models

Official models are always on, maintained, and have predictable pricing.

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

black-forest-labs/flux-canny-pro

Professional edge-guided image generation. Control structure and composition using Canny edge detection

Updated 92.2K runs

black-forest-labs/flux-fill-pro

Professional inpainting and outpainting model with state-of-the-art performance. Edit or extend images with natural, seamless results.

Updated 216.7K runs

Rembg implementation with mask output

Updated 42 runs

black-forest-labs/flux-1.1-pro

Faster, better FLUX Pro. Text-to-image model with excellent image quality, prompt adherence, and output diversity.

Updated 15.5M runs

Updated 1 run

black-forest-labs/flux-1.1-pro-ultra

FLUX1.1 [pro] in ultra and raw modes. Images are up to 4 megapixels. Use raw mode for realism.

Updated 5.9M runs

black-forest-labs/flux-pro

State-of-the-art image generation with top of the line prompt following, visual quality, image detail and output diversity.

Updated 9.3M runs

Janus-Pro is a novel autoregressive framework for multimodal understanding

Updated 1.9K runs

Generate music with YuE-s1-7B (English, chain of thought model)

Updated 366 runs

Test deployment of OuteTTS 500M

Updated 95 runs

Interior Design with RealVisXL V5.0-Lightning and ControlNet to generate photorealistic, high-resolution interior designs.

Updated 153 runs

Ultimate anime-themed finetuned SDXL model and the latest installment of the Animagine XL series

Updated 206 runs

black-forest-labs/flux-schnell

The fastest image generation model tailored for local development and personal use

Updated 223M runs

Interior Design with RealVisXL V5.0 and ControlNet (Depth & Union SDXL ProMax) to generate photorealistic, high-resolution interior designs with enhanced depth and structure.

Updated 114 runs

STAR Video Upscaler: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

Updated 222 runs

Updated 8 runs

Takes audio (mp3) and a "source-of-truth" audio transcript (string) as input and returns precise timestamps.

Updated 358 runs

Updated 11 runs

A demo model for a guide I'm working on...

Updated 5 runs

black-forest-labs/flux-fill-dev

Open-weight inpainting model for editing and extending images. Guidance-distilled from FLUX.1 Fill [pro].

Updated 110K runs

DeepSeek-R1 distilled on LLaMA3.3 70B and quantized by ollama

Updated 12 runs

Updated 10 runs

Updated 1 run

DeepSeek-R1 distilled on LLaMA 8B

Updated 243 runs

Updated 1 run

Updated 5 runs

Updated 6 runs

Kokoro v1.0 - text-to-speech (82M params, based on StyleTTS2)

Updated 146.1K runs

Updated 2 runs

Updated 6 runs

The VALL-E models by Amphion.

Updated 14 runs

The Vevo model by Amphion.

Updated 19 runs

Customise your hair with AI. Swap hair with anyone, copy anyone's hair color.

Updated 67 runs

Upscale videos + images with BSRGAN

Updated 1K runs

The MaskGCT model by Amphion.

Updated 6 runs

deepseek-ai/deepseek-r1

A reasoning model trained with reinforcement learning, on par with OpenAI o1

Updated 311.6K runs

The Fish Speech V1.2 SFT model.

Updated 6 runs

The Fish Speech V1.5 model.

Updated 11 runs

The Fish Speech V1.4 model.

Updated 3 runs

Adapted to have multi-lora support also for schnell: https://replicate.com/lucataco/flux-dev-multi-lora

Updated 2.2K runs

The Fish Speech V1.1 model.

Updated 2 runs

The Fish Speech V1.2 model.

Updated 2 runs

Cavalry 1 is a hello world model.

Updated 5 runs

Run any ComfyUI workflow on an A100. Guide: https://github.com/fofr/cog-comfyui

Updated 9.9K runs

The Fish Speech V1.0 model.

Updated 1 run

Create a dotted waveform video from an audio file

Updated 21 runs

Updated 10 runs

The small version of the Bark model by Suno.

Updated 13 runs

The Bark model by Suno.

Updated 31 runs

Updated 61 runs