Meta tags:
description=Run open-source machine learning models with a cloud API;

Headings (most frequently used words):

models, scale, run, build, and, fine, tune, deploy, custom, with, of, what, you, ai, products, all, one, line, code, aiwith, an, api, thousands, contributed, by, our, community, how, it, works, on, replicate, imagine, can, your, own, data, automatic, pay, for, use, forget, about, infrastructure, logging, monitoring,

Text of the page (most frequently used words):
and (52), runs (43), image (41), official (40), model (37), with (32), you (32), the (30), replicate (26), #models (24), for (22), generation (16), google (14), can (12), video (12), qwen (12), text (12), run (11), your (10), images (10), output (9), input (9), are (8), more (8), one (8), flux (8), openai (8), editing (8), high (8), pro (8), fast (8), bytedance (8), imagen (8), support (7), that (7), scale (7), use (7), single (7), prompt (7), new (7), version (7), line (6), fine (6), code (6), sec (6), gpu (6), resolution (6), seedream (6), ideogram (6), explore (5), get (5), language (5), how (5), nvidia (5), deploy (5), from (5), generate (5), black (5), forest (5), labs (5), latest (5), about (4), pricing (4), build (4), emojis (4), paint (4), autonomous (4), robots (4), api (4), our (4), self (4), predict (4), import (4), cog (4), own (4), custom (4), mattrothenberg (4), drone (4), art (4), create (4), tune (4), coding (4), improved (4), native (4), upscaler (4), optimized (4), philz1337x (4), claude (4), haiku (4), cost (4), than (4), speed (4), reve (4), faster (4), seedance (4), workflows (4), fidelity (4), adherence (4), flagship (4), audio (4), unified (4), precise (4), sentence (4), veo (4), turbo (4), fastest (4), quality (4), const (4), community (3), blog (3), docs (3), started (3), time (3), what (3), zero (3), open (3), source (3), predictions (3), throughput (3), machine (3), learning (3), don (3), pay (3), when (3), learn (3), enterprise (3), thousands (3), path (3), torch (3), sky (3), this (3), https (3), com (3), style (3), better (3), cinematic (3), but (3), complex (3), real (3), all (3), free (3), changelog (2), beta (2), playground (2), wordmark (2), glyph (2), like (2), next (2), command (2), interface (2), cli (2), tunes (2), never (2), gonna (2), give (2), ipad (2), app (2), lets (2), shot (2), imagine (2), let (2), particular (2), prediction (2), deploying (2), weights (2), gpus (2), only (2), running (2), not (2), using (2), a100 (2), 80gb (2), l40s (2), traffic (2), handle (2), demand (2), any (2), down (2), products (2), processed_image (2), def (2), takes (2), load (2), make (2), basepredictor (2), predictor (2), define (2), tok (2), rainbow (2), fantastical (2), drones (2), land (2), dev (2), data (2), ready (2), production (2), just (2), 432 (2), excelling (2), writing (2), reasoning (2), gpt (2), iteration (2), multi (2), consistency (2), controlnet (2), edit (2), plus (2), gemini (2), nano (2), banana (2), precision (2), portraits (2), faces (2), upscale (2), modes (2), powered (2), clarity (2), crystal (2), gives (2), similar (2), levels (2), performance (2), third (2), twice (2), anthropic (2), cheaper (2), ideal (2), rapid (2), ideation (2), mobile (2), perfect (2), creators (2), who (2), need (2), instant (2), feedback (2), previews (2), content (2), ltx (2), lightricks (2), 821 (2), realistic (2), human (2), motion (2), vfx (2), expressive (2), characters (2), strong (2), across (2), both (2), hailuo (2), minimax (2), synced (2), sora (2), higher (2), context (2), aware (2), reference (2), last (2), frame (2), demos (2), they (2), lucataco (2), mcai (2), pixray (2), tomasmcm (2), jbilcke (2), stability (2), vaibhavs10 (2), meta (2), zylim0702 (2), pagebrain (2), tstramer (2), pollinations (2), microsoft (2), research (2), prompthero (2), laion (2), fermatresearch (2), cheapest (2), creates (2), stunning (2), realism (2), creative (2), designs (2), consistent (2), styles (2), 527 (2), tailored (2), local (2), development (2), personal (2), schnell (2), 813 (2), foundation (2), series (2), achieves (2), significant (2), advances (2), rendering (2), excellent (2), diversity (2), important (2), try (2), sign (2), status, privacy, terms, join, home, company, github, discord, product, tools, vercel, wake, idea, watch, hit, front, page, hacker, news, bed, logo, metrics, keep, eye, performing, logs, zoom, debug, behaving, logging, monitoring, requests, per, second, hard, tried, know, servers, weird, dependencies, enormous, cuda, batching, forget, infrastructure, bills, long, expensive, them, 011200, 001400, 001950, 000975, 000225, 000100, cpu, ton, scales, automatically, charge, thing, automatic, plans, businesses, building, their, team, feature, day, millions, users, without, having, experts, postprocess, return, preprocess, description, grayscale, arguments, types, pth, into, memory, multiple, efficient, setup, class, python_packages, python_version, libglib2, libgl1, mesa, glx, system_packages, true, first, environment, yaml, care, generating, server, big, cluster, cloud, compute, aren, limited, tool, packaging, photo, forming, abcde1234, then, will, result, trigger_word, example, zip, input_images, 1000, steps, ostris, lora, trainer, e440909d3512c31646ee2e0c7d6f6f4923224863a6a10c494606e79fb5844497, destination, training, trainings, train, sdxl, person, object, improve, suited, specific, tasks, print, astronaut, riding, unicorn, dramatic, output_quality, jpg, output_format, num_outputs, aspect_ratio, has, already, published, these, things, works, push, shouldn, locked, inside, academic, papers, pushing, actually, work, have, apis, contributed, videos, caption, large, llms, restore, music, speech, log, console, await, process, replicate_api_token, env, auth, http, python, node, compare, menu,

Text of the page (random words):
replicate run ai with an api replicate glyph replicate wordmark explore pricing enterprise docs blog sign in try for free menu explore pricing enterprise docs blog sign in try for free compare models in the playground beta run ai with an api build and scale ai products run and fine tune models deploy custom models all with one line of code get started for free node python http import replicate from replicate const replicate new replicate auth process env replicate_api_token const model const input prompt const output await replicate run model input console log output with replicate you can generate images generate speech generate music restore images large language models llms caption images generate videos from images google imagen 4 fast use this fast version of imagen 4 when speed and cost are more important than quality 1 5m runs official bytedance seedream 4 unified text to image generation and precise single sentence editing at up to 4k resolution 5 5m runs official black forest labs flux 1 1 pro faster better flux pro text to image model with excellent image quality prompt adherence and output diversity 62 7m runs official qwen qwen image an image generation foundation model in the qwen series that achieves significant advances in complex text rendering 813 9k runs official black forest labs flux schnell the fastest image generation model tailored for local development and personal use 527 8m runs official ideogram ai ideogram v3 turbo turbo is the fastest and cheapest ideogram v3 v3 creates images with stunning realism creative designs and consistent styles 3 6m runs official bytedance seedream 3 a text to image model with support for native high resolution 2k image generation 2 8m runs official google imagen 4 google s imagen 4 flagship model 5 1m runs official google imagen 4 fast use this fast version of imagen 4 when speed and cost are more important than quality 1 5m runs official bytedance seedream 4 unified text to image generation and precise single sentence editing at up to 4k resolution 5 5m runs official black forest labs flux 1 1 pro faster better flux pro text to image model with excellent image quality prompt adherence and output diversity 62 7m runs official qwen qwen image an image generation foundation model in the qwen series that achieves significant advances in complex text rendering 813 9k runs official black forest labs flux schnell the fastest image generation model tailored for local development and personal use 527 8m runs official ideogram ai ideogram v3 turbo turbo is the fastest and cheapest ideogram v3 v3 creates images with stunning realism creative designs and consistent styles 3 6m runs official bytedance seedream 3 a text to image model with support for native high resolution 2k image generation 2 8m runs official google imagen 4 google s imagen 4 flagship model 5 1m runs official fermatresearch meta laion ai vaibhavs10 prompthero stability ai google research jbilcke microsoft tomasmcm pollinations pixray tstramer mcai pagebrain lucataco zylim0702 fermatresearch laion ai prompthero google research microsoft pollinations tstramer pagebrain zylim0702 meta vaibhavs10 stability ai jbilcke tomasmcm pixray mcai lucataco thousands of models contributed by our community all the latest models are on replicate they re not just demos they all actually work and have production ready apis ai shouldn t be locked up inside academic papers and demos make it real by pushing it to replicate explore models push a model google veo 3 1 new and improved version of veo 3 with higher fidelity video context aware audio reference image and last frame support 25 4k runs official bytedance seedream 4 unified text to image generation and precise single sentence editing at up to 4k resolution 5 5m runs official openai sora 2 openai s flagship video generation with synced audio 40 5k runs official minimax hailuo 2 3 a high fidelity video generation model optimized for realistic human motion cinematic vfx expressive characters and strong prompt and style adherence across both text to video and image to video workflows 821 runs official lightricks ltx 2 fast ideal for rapid ideation and mobile workflows perfect for creators who need instant feedback real time previews or high throughput content 3 8k runs official bytedance seedance 1 pro fast a faster and cheaper version of seedance 1 pro 8 5k runs official google veo 3 1 new and improved version of veo 3 with higher fidelity video context aware audio reference image and last frame support 25 4k runs official bytedance seedream 4 unified text to image generation and precise single sentence editing at up to 4k resolution 5 5m runs official openai sora 2 openai s flagship video generation with synced audio 40 5k runs official minimax hailuo 2 3 a high fidelity video generation model optimized for realistic human motion cinematic vfx expressive characters and strong prompt and style adherence across both text to video and image to video workflows 821 runs official lightricks ltx 2 fast ideal for rapid ideation and mobile workflows perfect for creators who need instant feedback real time previews or high throughput content 3 8k runs official bytedance seedance 1 pro fast a faster and cheaper version of seedance 1 pro 8 5k runs official reve create image generation model from reve 6 2k runs official anthropic claude 4 5 haiku claude haiku 4 5 gives you similar levels of coding performance but at one third the cost and more than twice the speed 3 5k runs official philz1337x crystal upscaler high precision image upscaler optimized for portraits and faces one of the upscale modes powered by clarity ai x https x com philz1337x 87 3k runs official google nano banana google s latest image editing model in gemini 2 5 26 4m runs official qwen qwen image edit plus the latest qwen image s iteration with improved multi image editing single image consistency and native support for controlnet 1 9m runs official openai gpt 5 openai s new model excelling at coding writing and reasoning 432 5k runs official reve create image generation model from reve 6 2k runs official anthropic claude 4 5 haiku claude haiku 4 5 gives you similar levels of coding performance but at one third the cost and more than twice the speed 3 5k runs official philz1337x crystal upscaler high precision image upscaler optimized for portraits and faces one of the upscale modes powered by clarity ai x https x com philz1337x 87 3k runs official google nano banana google s latest image editing model in gemini 2 5 26 4m runs official qwen qwen image edit plus the latest qwen image s iteration with improved multi image editing single image consistency and native support for controlnet 1 9m runs official openai gpt 5 openai s new model excelling at coding writing and reasoning 432 5k runs official how it works you can get started with any model with just one line of code but as you do more complex things you can fine tune models or deploy your own custom code run models our community has already published thousands of models that are ready to use in production you can run these with one line of code explore models import replicate output replicate run black forest labs flux dev input aspect_ratio 1 1 num_outputs 1 output_format jpg output_quality 80 prompt an astronaut riding a rainbow unicorn cinematic dramatic print output fine tune models with your own data you can improve models with your own data to create new models that are better suited to specific tasks image models like sdxl can generate images of a particular person object or style fine tune image models train a model training replicate trainings create destination mattrothenberg drone art version ostris flux dev lora trainer e440909d3512c31646ee2e0c7d6f6f4923224863a6a10c494606e79fb5844497 input steps 1000 input_images https example com images zip trigger_word tok this will result in a new model mattrothenberg drone art fantastical images of drones on land and in the sky 0 runs mattrothenberg drone art fantastical images of drones on land and in the sky 0 runs then you can run it with one line of code output replicate run mattrothenberg drone art abcde1234 input prompt a photo of tok forming a rainbow in the sky deploy custom models you aren t limited to the models on replicate you can deploy your own custom models using cog our open source tool for packaging machine learning models cog takes care of generating an api server and deploying it on a big cluster in the cloud we scale up and down to handle demand and you only pay for the compute that you use learn more first define the environment your model runs in with cog yaml build gpu true system_packages libgl1 mesa glx libglib2 0 0 python_version 3 10 python_packages torch 1 13 1 predict predict py predictor next define how predictions are run on your model with predict py from cog import basepredictor input path import torch class predictor basepredictor def setup self load the model into memory to make running multiple predictions efficient self model torch load weights pth the arguments and types the model takes as input def predict self image path input description grayscale input image path run a single prediction on the model processed_image preprocess image output self model processed_image return postprocess output scale on replicate thousands of businesses are building their ai products on replicate your team can deploy an ai feature in a day and scale to millions of users without having to be machine learning experts learn more about our enterprise plans automatic scale if you get a ton of traffic replicate scales up automatically to handle the demand if you don t get any traffic we scale down to zero and don t charge you a thing cpu 0 000100 sec nvidia t4 gpu 0 000225 sec nvidia l40s gpu 0 000975 sec 2x nvidia l40s gpu 0 001950 sec nvidia a100 80gb gpu 0 001400 sec 8x nvidia a100 80gb gpu 0 011200 sec learn more about pricing pay for what you use replicate only bills you for how long your code is running you don t pay for expensive gpus when you re not using them forget about infrastructure deploying machine learning models at scale is hard if you ve tried you know api servers weird dependencies enormous model weights cuda gpus batching prediction throughput requests per second logging monitoring metrics let you keep an eye on how your models are performing and logs let you zoom in on particular predictions to debug how your model is behaving replicate logo imagine what you can build autonomous robots zero shot autonomous robots with open source models paint with ai an ipad app that lets you paint with ai emojis sh ai emojis never gonna give you up video fine tunes on replicate language model cli language model command line interface imagine autonomous robots zero shot autonomous robots with open source models what you paint with ai an ipad app that lets you paint with ai can emojis sh ai emojis never gonna give you up video fine tunes on replicate build language model cli language model command line interface with replicate and tools like next js and vercel you can wake up with an idea and watch it hit the front page of hacker news by the time you go to bed get started replicate glyph replicate wordmark product explore playground beta pricing docs blog changelog community discord x github company home about changelog join us terms privacy status support