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

Tools to train a generative model on arbitrary audio samples

Updated 5.2K runs

High-Fidelity GAN Inversion for Image Attribute Editing

Updated 22.2K runs

a StyleGAN Encoder for Image-to-Image Translation

Updated 31.9K runs

ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement

Updated 98.5K runs

JoJoGAN: One Shot Face Stylization

Updated 496.1K runs

StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators

Updated 101.6K runs

Real-ESRGAN super-resolution model from ruDALL-E

Updated 484.2K runs

Detects any class given class names

Updated 28.1K runs

Image Restoration Using Swin Transformer

Updated 6M runs

Generate image captions

Updated 166.7M runs

Blind Face Restoration in the Wild

Updated 164.2K runs

Only a Matter of Style: Age Transformation Using a Style-Based Regression Model

Updated 1.3M runs

Simple image captioning model using CLIP and GPT-2

Updated 1.7M runs

Arbitrary Stylized Face Generation

Updated 7.6K runs

Bringing Old Photos Back to Life

Updated 1M runs

pix2pix model for predicting pbr texture maps from an albedo texture

Updated 7.4K runs

Generate subtitles from an audio file, using OpenAI's Whisper model.

Updated 73.2K runs

Detailed, higher-resolution images from Stable Diffusion

Updated 73K runs

任意のフレーズからジャパニーズヒップホップ風の歌詞を生成します

Updated 133 runs

Stable diffusion fork for generating tileable outputs

Updated 389.8K runs

openai/clip-vit-large-patch14 with Transformers

Updated 7.8M runs

stable-diffusion-textual-inversion fine-tuned with ugly sonic

Updated 2K runs

Generating Natural Images with Direct Patch Distribution Matching

Updated 5.9K runs

任意の日本語トピックからAIが長い文章を生成します

Updated 475 runs

Enhance Stable Diffusion prompt.

Updated 36.1K runs

Practical face restoration algorithm for *old photos* or *AI-generated faces*

Updated 33M runs

Japanese-specific latent text-to-image diffusion model

Updated 2.4K runs

stable-diffusion-textual-inversion fine-tuned with spyro of the dragon STYLE

Updated 477 runs

Practical Image Restoration Algorithms for General/Anime Images

Updated 7.2M runs

Use stable diffusion and aesthetic CLIP embeddings to guide boring outputs to be more aesthetically pleasing.

Updated 4.3K runs

Activating More Pixels in Image Super-Resolution Transformer

Updated 25.1K runs

End-to-End Document Image Enhancement Transformer

Updated 4.6K runs

(development branch) Inpainting for Stable Diffusion

Updated 13.4K runs

Entity linking to wikipedia pages using facebook's GENRE

Updated 43 runs

[CASUAL] A Neural Language Style Transfer framework to transfer styles on natural language text

Updated 29 runs

[PASSIVE VOICE] A Neural Language Style Transfer framework to transfer styles on natural language text

Updated 74 runs

A Neural Language Style Transfer framework to transfer styles on natural language text

Updated 114 runs

Get an approximate text prompt, with style, matching an image. (Optimized for stable-diffusion (clip ViT-L/14))

Updated 2.7M runs

Sentence embedding using mpnet

Updated 45.8K runs

Embedding generation using microsoft's xtremedistil-l6-h384-uncased model

Updated 18 runs

Updated 2.6K runs

Updated 55 runs

Text summarization using brio-xsum-cased model

Updated 501 runs

Pose-Invariant Hairstyle Transfer

Updated 9.9K runs

Colab version of AI Dungeon

Updated 366 runs

Generate music based on the Monkey Island theme using the FIGARO model

Updated 305 runs

Generate 768px images from text using CompVis `retrieval-augmented-diffusion`

Updated 38.4K runs

Monkey Island database for Retrieval-augmented Diffusion model

Updated 623 runs