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

Make 3D stuff

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

Restore images

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

Make videos with Wan2.1

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

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.

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.

Use FLUX fine-tunes

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

Latest models

Text to image prompt

Updated 1.1K runs

Create song covers with any RVC v2 trained AI voice from audio files.

Updated 834.7K runs

Ultimate SD Upscale with ControlNet Tile

Updated 162K runs

A combination of ip_adapter SDv1.5 and mediapipe-face to inpaint a face

Updated 4.1K runs

The Yi series models are large language models trained from scratch by developers at 01.AI.

Updated 1.7K runs

The Yi series models are large language models trained from scratch by developers at 01.AI.

Updated 3.7K runs

The Yi series models are large language models trained from scratch by developers at 01.AI.

Updated 161.1K runs

Creates an SD illusion from drawing + adds depth

Updated 330 runs

Custom improvements like a custom callback to enhance the inference | It's a WIP and it may causes some wrong outputs

Updated 1.3K runs

An extremely fast all-in-one model to use LCM with SDXL, ControlNet and custom LoRA url's!

Updated 14.8K runs

Create variations of an uploaded image. Please see README for more details

Updated 1.1K runs

Whisper is a general-purpose speech recognition model.

Updated 4.4K runs

SDXL_Niji_Special Edition

Updated 79.6K runs

Source: meta-llama/Llama-2-7b-chat-hf ✦ Quant: TheBloke/Llama-2-7B-Chat-AWQ ✦ Intended for assistant-like chat

Updated 77 runs

Source: meta-math/MetaMath-Mistral-7B ✦ Quant: TheBloke/MetaMath-Mistral-7B-AWQ ✦ Bootstrap Your Own Mathematical Questions for Large Language Models

Updated 393 runs

Source: Severian/ANIMA-Phi-Neptune-Mistral-7B ✦ Quant: TheBloke/ANIMA-Phi-Neptune-Mistral-7B-AWQ ✦ Biomimicry Enhanced LLM

Updated 22 runs

explore img2img zooming sdxl

Updated 1.1K runs

Make variations of an image with SDXL

Updated 387 runs

Updated 27 runs

Latent Consistency Model (LCM): SDXL, distills the original model into a version that requires fewer steps (4 to 8 instead of the original 25 to 50)

Updated 395.6K runs

Generate high-quality images faster with Latent Consistency Models (LCM), a novel approach that distills the original model, reducing the steps required from 25-50 to just 4-8 in Stable Diffusion (SDXL) image generation.

Updated 2.3K runs

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate SDXL images with an image prompt

Updated 33.4K runs

Updated 52 runs

batch or individual face detection with mediapipe

Updated 86.7K runs

Canny, soft edge, depth, lineart, segmentation, pose, etc

Updated 41.5K runs

POC of SDXL-LCM LoRA combined with a Replicate LoRA for 4 second inference time

Updated 354 runs

Updated 427 runs

Updated 257 runs

Updated 98 runs

EpicRealism with all Controlnet Models included

Updated 275 runs

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate SDXL images with an image prompt

Updated 1.9K runs

Latent Consistency Model (LCM): SSD-1B, is a LCM distilled version that reduces the number of inference steps needed to only 2 - 8 steps

Updated 1.6K runs

QR Code AI Art Generator

Updated 4.1K runs

Updated 60 runs

OpenChat: Advancing Open-source Language Models with Mixed-Quality Data

Updated 110.8K runs

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate SDv1.5 images with an image prompt

Updated 2.5K runs

Updated 199.3K runs

Updated 68.4K runs

Implementation of SDXL RealVisXL_V2.0

Updated 287.6K runs

Updated 856 runs

POC to run inference on Realvisxl2 LoRAs

Updated 3.2K runs

POC to train Realvisxl2 LoRAs

Updated 453 runs

Segmind Stable Diffusion Model (SSD-1B) is a distilled 50% smaller version of SDXL, offering a 60% speedup while maintaining high-quality text-to-image generation capabilities

Updated 1M runs

POC to run inference on SSD-1B LoRAs

Updated 2.7K runs

POC to train SSD-1B LoRAs for cheaper & faster training

Updated 262 runs

Batch mode for Segmind Stable Diffusion Model (SSD-1B) txt2img

Updated 1.2K runs

Gorilla: Large Language Model Connected with Massive APIs

Updated 91 runs

Updated 12.1K runs

Implementation of SDXL RealVisXL_V2.0 img2img

Updated 8.9K runs