Explore

Fine-tune FLUX fast

Customize FLUX.1 [dev] with the fast FLUX trainer on Replicate

Train the model to recognize and generate new concepts using a small set of example images, for specific styles, characters, or objects. It's fast (under 2 minutes), cheap (under $2), and gives you a warm, runnable model plus LoRA weights to download.

Official models

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

View all official models

I want to…

Upscale images

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

Restore images

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

Enhance videos

Upscaling models that create high-quality video from low-quality videos

Make videos with Wan

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

Use Kontext fine-tunes

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

Make 3D stuff

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

Control image generation

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

Try for free

Get started with these models without adding a credit card. Whether you're making videos, generating images, or upscaling photos, these are great starting points.

Use official models

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

Detect objects

Models that detect or segment objects in images and videos.

Use FLUX fine-tunes

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

Latest models

Split one or multiple images into four equal parts

Updated 60 runs

Text-to-Video + Image-to-Video: Pyramid Flow Autoregressive Video Generation method based on Flow Matching

Updated 8.7K runs

FLUX.1-Dev LoRA Training by Huggingface Diffusers

Updated 222 runs

Fun & Pro for Every Occasion, Just Shoot at https://HeadShots.fun/

Updated 8.3K runs

Updated 8 runs

Updated 227 runs

XLabs v3 canny, depth and soft edge controlnets for Flux.1 Dev

Updated 235.8K runs

test-world

Updated 5 runs

test-world

Updated 13 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 30K runs

Mobius: Redefining State-of-the-Art in Debiased Diffusion Models

Updated 131 runs

Diffusion-based Visual Foundation Model for High-quality Dense Prediction

Updated 371 runs

FLUX.1-Dev LoRA Explorer (DEPRECATED Please use: black-forest-labs/flux-dev-lora)

Updated 3.8M runs

This is a test version, more updates coming

Updated 249 runs

Transcribes audio using Whisper Large V3 with precise word-level timestamps and confidence scores.

Updated 5.6K runs

Generates subtitles from audio using whisperX (faster-whisper-large-v3)

Updated 1.2K runs

A soon-to-be accelerated endpoint for multi-modal inference.

Updated 201 runs

Controlnet trained on black-forest-labs/FLUX.1-dev with lineart condition

Updated 353 runs

Add or change what you want on your image

Updated 2.7K runs

Updated 89 runs

Generating Consistent Long Depth Sequences for Open-world Videos

Updated 205 runs

Erase what you don't want on your image

Updated 383 runs

Emu3-Chat for vision-language understanding

Updated 28 runs

Emu3-Gen for image generation

Updated 54 runs

Updated 12.8K runs

allenai/Molmo-7B-D-0924, Answers questions and caption about images

Updated 125.4K runs

🎼FluxMusic Text-to-Music Generation with Rectified Flow Transformer🎶

Updated 8.5K runs

Meta Llama 3.2 1B

Updated 2.7K runs

Meta Llama 3.2 1B

Updated 198 runs

Omni-Zero Couples: A diffusion pipeline for zero-shot stylized couples portrait creation.

Updated 18.6K runs

Bielik-11B-v2.3-Instruct is a generative text model made by SpeakLeash and Cyfronet featuring 11 billion parameters. It is a linear merge of the Bielik-11B-v2.0-Instruct, Bielik-11B-v2.1-Instruct, and Bielik-11B-v2.2-Instruct models.

Updated 1.4K runs

Implementation of tencent-ailab/IP-Adapter with ip-adapter-plus-face_sd15

Updated 163 runs

CogVLM2: Visual Language Models for Image and Video Understanding

Updated 656.8K runs

CogVLM2: Visual Language Models for Image and Video Understanding

Updated 627 runs

Quickly edit the expression of a face

Updated 77.9K runs

Seamless Speech Interaction with Large Language Models

Updated 60.1K runs

Ollama Qwen2.5 72b

Updated 25.8K runs

Image-to-Video Diffusion Models with An Expert Transformer

Updated 998 runs

Text-to-Video Diffusion Models with An Expert Transformer

Updated 253 runs

Explore how Flux Dev responds when you change the strengths of layers in the model. See readme for examples of how to select layers.

Updated 8.5K runs

Image Caption model

Updated 393 runs

FLUX.1-dev Inpainting ControlNet model

Updated 7.8K runs

Create lifelike interior designs with AI from text descriptions and image references.

Updated 6.1K runs

Run inpainting with Flux, compatible with Canny ControlNet, LoRAs and HyperFlux_8step

Updated 30.8K runs

An experimental flux based model for creative research

Updated 142 runs

SD1.5 Canny controlnet with LoRA support.

Updated 548.8K runs

⚡️FLUX PuLID: FLUX-dev based Pure and Lightning ID Customization via Contrastive Alignment🎭

Updated 2.2M runs

Controlling SD XL diffusion inference

Updated 11 runs

Interior remodelling, keeps windows, ceilings, and doors. Uses a depth controlnet weighted to ignore existing furniture.

Updated 27.6K runs

Match facial expression using a driving image using LivePortrait as a base

Updated 119K runs