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

Automatically add captions to a video

Updated 46K runs

Updated 263 runs

this is the replicate version of singing_voice_conversion from amphion

Updated 573 runs

Animagine XL 2.0 is an advanced latent text-to-image diffusion model designed to create high-resolution, detailed anime images.

Updated 9.3K runs

ElasticDiffusion: Training-free Arbitrary Size Image Generation

Updated 170 runs

Super High Quality Depth Maps 🗺️: An End-to-End Tile-Based Framework 🏗️ for High-Resolution Monocular Metric Depth Estimation 🔍📏

Updated 374 runs

A unique fusion that showcases exceptional prompt adherence and semantic understanding, it seems to be a step above base SDXL and a step closer to DALLE-3 in terms of prompt comprehension

Updated 127.4K runs

Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer

Updated 178 runs

Nous Hermes 2 - Yi-34B is a state of the art Yi Fine-tune, fine tuned on GPT-4 generated synthetic data

Updated 11.6K runs

Terminus XL Otaku is a latent diffusion model that uses zero-terminal SNR noise schedule and velocity prediction objective at training and inference time.

Updated 42 runs

works with inpainting and multi-controlnet + single-controlnet || ip-adapter + without ip adapter

Updated 23.8K runs

Rethinking the Role of UNet Encoder in Diffusion Models

Updated 133 runs

Updated 269.9K runs

Terminus XL Gamma is a new state-of-the-art latent diffusion model that uses zero-terminal SNR noise schedule and velocity prediction objective at training and inference time.

Updated 279 runs

Source: SuperAGI/SAM ✦ Quant: TheBloke/SAM-AWQ ✦ SAM (Small Agentic Model), a 7B model that demonstrates impressive reasoning abilities despite its smaller size

Updated 78 runs

Multi-controlnet, lora loading, img2img, inpainting

Updated 211.7K runs

High-Fidelity Text-to-3D Generation via Interval Score Matching

Updated 71 runs

Try out akx/Poro-34B-gguf, Q5_K, This is 1000B checkpoint model

Updated 28 runs

Amphion Singing Voice Conversion: DiffWaveNetSVC

Updated 980 runs

DreamBooth safetensors model use RealVisXL

Updated 757 runs

Amazing photorealism with RealVisXL_V3.0, based on SDXL, trainable

Updated 747.3K runs

Cog implementation of mir-aidj(Taejun Kim)'s 'All-In-One Music Structure Analyzer'

Updated 26.2K runs

(Research only) IP-Adapter-FaceID can generate various style images conditioned on a face with only text prompts

Updated 30.8K runs

DreamShaper is a general purpose SD model that aims at doing everything well, photos, art, anime, manga. It's designed to go against other general purpose models and pipelines like Midjourney and DALL-E.

Updated 1.4K runs

DPO-SDXL Canny controlnet with LoRA support.

Updated 774 runs

Segment Anything MASK

Updated 1.3K runs

DreamShaper is a general purpose SD model that aims at doing everything well, photos, art, anime, manga. It's designed to match Midjourney and DALL-E.

Updated 223.2K runs

Direct Preference Optimization (DPO) is a method to align diffusion models to text human preferences by directly optimizing on human comparison data

Updated 2.2K runs

auto1111_ds8

Updated 61.8K runs

FacebookResearch/SeamlessM4T v2 - Massively Multilingual & Multimodal Machine Translation

Updated 806 runs

Updated 365 runs

The "Overall Best Performing Open Source 7B Model" for Coding + Generalization or Mathematical Reasoning

Updated 26.3K runs

Updated 64 runs

Source: kaist-ai/prometheus-13b-v1.0 ✦ Quant: TheBloke/prometheus-13B-v1.0-AWQ ✦ An alternative to GPT-4 when evaluating LLMs & Reward models for RLHF

Updated 54K runs

Source: OpenBuddy/openbuddy-zephyr-7b-v14.1 ✦ Quant: TheBloke/openbuddy-zephyr-7B-v14.1-AWQ ✦ Open Multilingual Chatbot

Updated 31 runs

AnimateDiff v3 + SparseCtrl: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning. Created with Shimmer.

Updated 695 runs

Blue Pencil XL v2 Model (Text2Img, Img2Img and Inpainting)

Updated 302K runs

SDXL image generation using ComfyUI with LoRA trained on DreamBooth method.

Updated 213 runs

korean version of llava-v1.5

Updated 66 runs

Stable Diffusion x4 upscaler model

Updated 7.5K runs

Speaker diarisation

Updated 32 runs

Source: upstage/SOLAR-10.7B-Instruct-v1.0 ✦ Quant: TheBloke/SOLAR-10.7B-Instruct-v1.0-AWQ ✦ Elevating Performance with Upstage Depth UP Scaling!

Updated 4.1K runs

an autocomplete api that runs on the cpu :)

Updated 19.5K runs

Monocular depth estimation

Updated 8.6K runs

AI-driven audio enhancement for your audio files, powered by Resemble AI

Updated 138.3K runs

Zero-shot speech synthesizer for text-to-speech and voice conversion

Updated 4.6K runs

A quantized 34B parameter language model from Phind for code completion

Updated 231 runs

LLMs with open-source code snippets for generating low-bias and high-quality instruction data for code.

Updated 361 runs

Open-source Distilled Stable Diffusion 100% speedup

Updated 1.7K runs