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

GLM-4V is a multimodal model released by Tsinghua University that is competitive with GPT-4o and establishes a new SOTA on several benchmarks, including OCR.

Updated 88.2K runs

Convert speech in audio to text w/ `tiny`, `small`, `base`, and `large-v3` models

Updated 129 runs

Extended video synthesis model that generates 128 frames

Updated 204 runs

Image generation, Inpaint Strength, loras custom_urls and enhancer.

Updated 447 runs

Depth estimation with faster inference speed, fewer parameters, and higher depth accuracy.

Updated 198K runs

Updated 20 runs

Hermes 2 Pro is an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house

Updated 344 runs

Best Open-Source Model for Function Calling

Updated 33 runs

Speech to speech with any RVC v2 trained AI voice

Updated 817K runs

hello world

Updated 47 runs

Google's Gemma2 27b instruct model

Updated 12.9K runs

AuraSR: GAN-based Super-Resolution for real-world

Updated 2.8K runs

Google's Gemma2 9b instruct model

Updated 23.6K runs

Model

Updated 412 runs

A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Updated 1.1K runs

Model that generates Cartoon like characters

Updated 770 runs

Stable Diffusion 3 with Differential Diffusion inpainting (experimental)

Updated 271 runs

Fork of https://replicate.com/schananas/grounded_sam that uses OwlV2 instead of Grounding Dino

Updated 3.7K runs

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

Updated 169.6K runs

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

Updated 70.1K runs

Updated 495 runs

Qwen 2: A 7 billion parameter language model from Alibaba Cloud, fine tuned for chat completions

Updated 1.8K runs

Qwen 2: A 1.5 billion parameter language model from Alibaba Cloud, fine tuned for chat completions

Updated 220 runs

A novel speech model for insane prosody.

Updated 479 runs

Qwen 2: A 0.5 billion parameter language model from Alibaba Cloud, fine tuned for chat completions

Updated 200 runs

good for video teaser backsound

Updated 62 runs

High resolution image Upscaler and Enhancer. Use at ClarityAI.co. A free Magnific alternative. Twitter/X: @philz1337x

Updated 16.2M runs

Updated 515 runs

✨Stable Diffusion 3 w/ ⚡InstantX's Canny, Pose, and Tile ControlNets🖼️

Updated 1.3K runs

A model for experimenting with all the SD3 settings. Non-commercial use only, unless you have a Stability AI Self Hosted License.

Updated 32.2K runs

Updated 181 runs

Stable Audio Open is an open-source model optimized for generating short audio samples, sound effects, and production elements using text prompts.

Updated 20.4K runs

Stable Diffusion 3 medium with added variability in outputs. Non-commercial use only, unless you have a Stability AI Self Hosted License.

Updated 20.2K runs

Transcribe saxophone solos directly from audio

Updated 202 runs

Real-Time Open-Vocabulary Object Detection using the xl weights

Updated 771.6K runs

MusicGen running on an a40 with 60 seconds max duration

Updated 1.2K runs

Updated 177 runs

Mobius, a diffusion model that pushes the boundaries of domain-agnostic debiasing and representation realignment

Updated 625 runs

DOVER video quality assessment tool, assigning videos both aesthetic and technical quality scores

Updated 27 runs

Generate Product photography backgrounds using Stable Diffusion

Updated 538 runs

DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation. Hologram optimized

Updated 350 runs

Transfer learning models for music classification by genres, moods, and instrumentation

Updated 10.6K runs

🫦 Realistic facial expression manipulation (lip-syncing) using audio or video

Updated 1.1K runs

Super fast clothing (and face) segmentation and masking with erosion and dilation capability, made for https://outfit.fm

Updated 17.7K runs

The best Pony-SDXL models! Current one is based on Pony Realism.

Updated 110.4K runs

# Interior Decoration Space Scaling - First Use Case

Updated 66 runs

A tiny model for testing out Cog

Updated 1.1K runs