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…

Make videos with Wan2.1

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

Restore images

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

Upscale images

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

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

Real-ESRGAN Video Upscaler

Updated 230.4K runs

Granite-Embedding-278M-Multilingual is a 278M parameter model from the Granite Embeddings suite that can be used to generate high quality text embeddings

Updated 924 runs

Updated 130 runs

Photomaker V1 optimized with Lightning 8steps

Updated 440 runs

Revival of https://github.com/pollinations/stable-diffusion-audio-reactive

Updated 7 runs

The original classic DALLᐧE 2

Updated 144 runs

An AI system that can create realistic images and art from a description in natural language.

Updated 889 runs

Color match and white balance fixes for images

Updated 21.6K runs

A powerful 3D asset generation model

Updated 175.1K runs

🕹️FramePack: video diffusion that feels like image diffusion🎥

Updated 1.8K runs

A Step Towards Music Generation Foundation Model text2music

Updated 3.4K runs

This a pruna optimised version of the flux 1.dev model.

Updated 40.7K runs

DiT-based 13b video generation model, creating 30fps video

Updated 1.2K runs

..

Updated 93.5K runs

👗Bytedance's DreamO: unified image customization model (IP, ID, Style, Try-On, etc.)🧣

Updated 711 runs

Updated 99 runs

Models fine-tuned from NoobAI-XL/Illustrious-XL series.

Updated 32.9K runs

Models fine-tuned from Pony-XL series.

Updated 520.1K runs

GPU accelerated replay renderer / video data clipper for comma.ai connect's openpilot route data. SEE README.

Updated 4.4K runs

Uses DINO to detect regions and further refines them with SAM. Returns masking data as RLE encoded JSON.

Updated 276 runs

FramePack video generation with image + motion prompt. Based on Stanford's 2025 model.

Updated 85 runs

Updated 218 runs

An enhanced version of sd-interior-design, featuring improved diffusion model

Updated 2.3K runs

Text-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities. Designed for real-time applications with low latency

Updated 50.4K runs

Text-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities. Optimized for high-fidelity applications like voiceovers and audiobooks.

Updated 92.2K runs

An enhanced version of sd-interior-design

Updated 88 runs

Clone voices to use with Minimax's speech-02-hd and speech-02-turbo

Updated 4K runs

Updated 14K runs

A 2x faster qwen 3 model through pruna oss

Updated 21.2K runs

This is the hidream-e1 model accelerated with the pruna optimisation engine.

Updated 19.5K runs

Updated 511 runs

🎧 Kimi-Audio-7B-Instruct, ASR, audio reasoning, captioning, emotion sensing, and TTS into one universal model 🔊

Updated 216 runs

✍️Step1X-Edit by stepfun-ai, Edit an image using text prompt📸

Updated 11.8K runs

Balance speed, quality and cost. Ideogram v3 creates images with stunning realism, creative designs, and consistent styles

Updated 39.5K runs

Turbo is the fastest and cheapest Ideogram v3. v3 creates images with stunning realism, creative designs, and consistent styles

Updated 177.8K runs

The highest quality Ideogram v3 model. v3 creates images with stunning realism, creative designs, and consistent styles

Updated 76.9K runs

This is the f-lite model from FAL & Freepik optimised for 2x speedups through pruna

Updated 129 runs

Use one or two face images to create AI avatars

Updated 5K runs

Classifies Pokémon Yellow game screens for automated gameplay (Battle, Menu, Overworld, Dialogue)

Updated 2.5K runs

Train FLUX.1 [pro] and FLUX 1.1 [pro] Ultra. Upload images to create a custom finetune_id to use with the inference model

Updated 1.3K runs

A multimodal image generation model that creates high-quality images. You need to bring your own verified OpenAI key to use this model. Your OpenAI account will be charged for usage.

Updated 73.2K runs

SOTA image-to-3D generator TRELLIS. Equipped with **All image-condition types** you need: (1) single-image (2) multi-images (3) different images for geometry and texture generation (4) mesh+images for detail variation(texture painting)

Updated 141 runs

Enhance Generation Quality of Flow Matching V2A Model via Multi-Step CoT-Like Guidance and Combined Preference Optimization

Updated 34 runs

IMG2IMG for HiDream FULL AND DEV - does creative variations

Updated 677 runs

Minimax's first image model, with character reference support

Updated 406.9K runs

Professional-grade image upscaling, from Topaz Labs

Updated 54.9K runs

KCV Final Project Model :3

Updated 101 runs

Video Upscaling from Topaz Labs

Updated 31.7K runs