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.

I want to…

Make videos with Wan2.1

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

Upscale images

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

Restore images

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

Use official models

Official models are always on, maintained, and have predictable pricing.

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

Optimizes audio files with speech

Updated 7 runs

Take any low quality AI photo and make it realistic. Image enhancement that eliminates artifacts, adds natural depth, improves details, and upscales with photorealistic quality for stunning, professional results. ⚠️Expensive: ~0.35 $/image (2x upscale)

Updated 205 runs

Updated 22.2K runs

Lyria 2 is a music generation model that produces 48kHz stereo audio through text-based prompts

Updated 1K runs

Generate 5s and 9s 720p videos, faster and cheaper than Ray 2

Updated 16.2K runs

Generate 5s and 9s 720p videos

Updated 18.6K runs

Train subjects or styles faster than ever

Updated 241 runs

Generate 5s and 9s 540p videos

Updated 3.1K runs

Fast, high quality text-to-video and image-to-video (Also known as Dream Machine)

Updated 33.6K runs

Updated 4.4K runs

🥯ByteDance Seed's Bagel Unified multimodal AI that generates images, edits images, and understands images in one 7B parameter model🥯

Updated 160 runs

State of the art video generation model. Veo 2 can faithfully follow simple and complex instructions, and convincingly simulates real-world physics as well as a wide range of visual styles.

Updated 49.4K runs

A version of flux-dev, a text to image model, that supports fast fine-tuned lora inference

Updated 1.7M runs

Claude Sonnet 4 is a significant upgrade to 3.7, delivering superior coding and reasoning while responding more precisely to your instructions

Updated 4.1K runs

Transform PDFs into AI podcasts for engaging on-the-go audio content.

Updated 41 runs

Preview of Google's Imagen-4 flagship model. As a preview, this model might change.

Updated 21.6K runs

A faster and cheaper Imagen 3 model, for when price or speed are more important than final image quality

Updated 133.1K runs

Google's highest quality text-to-image model, capable of generating images with detail, rich lighting and beauty

Updated 927.1K runs

Scaling Diffusion Models for High Resolution Textured 3D Assets Generation

Updated 9.2K runs

Updated 241 runs

Generate 5s and 10s videos in 1080p resolution

Updated 316.1K runs

This model generates pose variation of a cartoon character. It preserves the cartoon identity. Use this model to augment training dataset for any cartoon character created through AI. The augmented dataset can be used to train a LoRA model.

Updated 5K runs

Generate 5s and 10s videos in 720p resolution at 30fps

Updated 601.3K runs

Quickly make 5s or 8s videos at 540p, 720p or 1080p. It has enhanced motion, prompt coherence and handles complex actions well.

Updated 5.5K runs

Quickly generate smooth 5s or 8s videos at 540p, 720p or 1080p

Updated 12K runs

MEMO is a state-of-the-art open-weight model for audio-driven talking video generation.

Updated 751 runs

A speech-to-text model that uses GPT-4o to transcribe audio

Updated 197 runs

A speech-to-text model that uses GPT-4o mini to transcribe audio

Updated 41 runs

🧼Upscales faces in videos look to be clearer and better using KEEP, Kalman-Inspired Feature Propagation for Video Face Super-Resolution🫟

Updated 35 runs

OpenAI's fast, lightweight reasoning model

Updated 334 runs

This is an optimised version of the flux schnell model from black forest labs with the pruna tool. We achieve a ~3x speedup over the original model with minimal quality loss.

Updated 9.3K runs

OpenAI's first o-series reasoning model

Updated 1.9K runs

A small model alternative to o1

Updated 6 runs

OpenAI's high-intelligence chat model

Updated 13.7K runs

Low latency, low cost version of OpenAI's GPT-4o model

Updated 1.4K runs

OpenAI's Flagship GPT model for complex tasks.

Updated 994 runs

Fastest, most cost-effective GPT-4.1 model from OpenAI

Updated 166 runs

Fast, affordable version of GPT-4.1

Updated 196 runs

Real-ESRGAN Video Upscaler

Updated 220.1K 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 14 runs

This is VACE-14B model optimised with pruna ai. Wan2.1 VACE is an all-in-one model for video creation and editing.

Updated 2.8K runs

Updated 130 runs

Photomaker V1 optimized with Lightning 8steps

Updated 152 runs

Generate 5s and 10s videos in 720p resolution

Updated 18K runs

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

Updated 4 runs