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.

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

Inference on Realistic Vision XL 4.0 - Use any LoRA model

Updated 473 runs

High quality image blending using Kandinsky 2.2 blending pipeline brought to you by your best friends at FullJourney.AI :)

Updated 77.9K runs

Updated 72 runs

Updated 88 runs

Updated 628 runs

Monster Labs' control_v1p_sd15_qrcode_monster ControlNet on top of SD 1.5

Updated 405.3K runs

Generate "algorithmic symphony" one-liners with grammar-constrained CodeLlama

Updated 207 runs

A facial animation generator model based on diffusion

Updated 205 runs

Fast automatic speech recognition (70x realtime with large-v2) with word-level timestamps and speaker diarization.

Updated 14.7K runs

Fast Diffusion for Image Generation, ~3 Seconds

Updated 2K runs

Updated 3.2K runs

Efficient Pretraining of Text-to-Image Models

Updated 4.2K runs

Product advertising image generator using SDXL

Updated 390K runs

Image Mixer Stable Diffusion

Updated 14.4K runs

Remove background from an image

Updated 8.6M runs

Updated 40 runs

Fashion model

Updated 470 runs

stream previews as it is generated

Updated 688 runs

SeamlessM4T—Massively Multilingual & Multimodal Machine Translation

Updated 83.6K runs

A 70 billion parameter language model from Meta, fine tuned for chat completions

Updated 9.5M runs

Base version of Llama 2, a 70 billion parameter language model from Meta.

Updated 352K runs

A 13 billion parameter language model from Meta, fine tuned for chat completions

Updated 4.9M runs

Base version of Llama 2 13B, a 13 billion parameter language model

Updated 201.8K runs

Base version of Llama 2 7B, a 7 billion parameter language model

Updated 651.6K runs

Updated 56 runs

Implementation of SDXL RealVisXL_V1.0

Updated 44.2K runs

SDXL ControlNet - Depth

Updated 31.2K runs

CLIP Interrogator (for faster inference)

Updated 123K runs

Updated 266 runs

Updated 46 runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 3.6K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 7K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 1.5K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 10.7K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 9.6K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 948 runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 1.2K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 5.4K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 60.7K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 1.7K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 10.2K runs

T4 GPU, negative embeddings,img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 9.5K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 21.6K runs

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Updated 7.1K runs

Updated 26 runs

The CLIP Interrogator is a prompt engineering tool that combines OpenAI's CLIP and Salesforce's BLIP to optimize text prompts to match a given image. Use the resulting prompts with text-to-image models like Stable Diffusion to create cool art!

Updated 3.9M runs

360 Panorama SDXL image with inpainted wrapping seam

Updated 6.4K runs

PyTorch version of Lightweight OpenPose as introduced in "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose"

Updated 1.6K runs

LLAMA-2 7b chat version by Meta. Stream support. Unaltered prompt. Temperature working properly. Economical hardware.

Updated 284 runs

Updated 565 runs