# Orisu

> Orisu makes AI ad creative for ecommerce and DTC brands, performance marketers and agencies. You write one brief and get on-brand product images, UGC-style video ads with AI actors, voiceover and localization into 78 languages, built as a workflow on a visual canvas that you can rerun for the next product. Feed runs the same workflow across a whole product catalog, Brain keeps your brand's facts and rules in one place, and an MCP server lets Claude and ChatGPT run it all from a chat. 100+ image, video, voice and text models are included in one subscription.

Key facts:
- Product category: AI ad creative platform (images, video ads, voice) built on a node-workflow canvas
- Audience: ecommerce and DTC brands, performance marketers and media buyers, agencies running several client brands
- Outputs: product photos and lifestyle scenes, static ads, UGC-style video ads with AI actors and lip-sync, voiceover, localization into 78 languages (translated, re-voiced and lip-synced), captions, every channel size
- Workflows: visible node graphs on a canvas; rerun one with a new product, hook or market instead of starting over; share as App Mode apps teammates can run without the canvas
- Bulk: Feed runs one workflow across every row of a product catalog and exports a feed Meta and TikTok can pull
- Brand: a brand kit built from your website URL (colors, fonts, voice, logo); Brain stores brand facts and rules that every workflow, teammate and assistant reads
- Assistants: MCP server for Claude and ChatGPT (build, run and review workflows from a chat); public REST API
- Models: 100+ models from Google, OpenAI, Black Forest Labs, Kling, Seedance, ElevenLabs and others, one subscription
- Pricing: Free $0 (100 credits a month, about 10 Nano Banana 2 images, no credit card), Starter $19/month (1,000 credits), Pro $49/month (5,000 credits), Enterprise $300/month (25,000 credits). Every node shows its credit cost before it runs.

## Product

- [Home](https://orisu.ai/): What Orisu makes and how a brief becomes a campaign
- [Brain](https://orisu.ai/product/brain): Teach Orisu your brand once; every agent, teammate and assistant works from the same knowledge
- [Feed](https://orisu.ai/product/feed): Run one creative workflow across a whole product catalog and export a feed Meta and TikTok pull
- [The Canvas](https://orisu.ai/product/canvas): Visible node workflows you can rewire and rerun
- [App Mode](https://orisu.ai/product/app-mode): Any workflow as a simple app the whole team can run
- [Brand Kit](https://orisu.ai/product/brand-kit): Paste a URL, get your brand applied to every output
- [API and MCP](https://orisu.ai/product/api): Run Orisu workflows from your own code or from Claude and ChatGPT; the canvas renders inside the chat
- [API and MCP, agent view](https://orisu.ai/product/api.md): The same page as plain markdown for agents: endpoints, MCP setup and tools
- [Templates](https://orisu.ai/templates): Runnable community workflows
- [Pricing](https://orisu.ai/pricing): Plans and credits
- [Machine-readable pricing](https://orisu.ai/pricing.md): Structured plan/limit/price data for agents

## Prompt library

Free, copyable prompts and multi-step workflows for image and video models, each with example output and credit to its creator. Every entry has a markdown version at https://orisu.ai/prompts/<slug>/md.

- [Prompt library](https://orisu.ai/prompts): Browse every prompt, newest first
- [Prompt library index for LLMs](https://orisu.ai/prompts/llms.txt): Hubs plus the top 500 prompts, linked to their markdown versions
- [Marketing prompts](https://orisu.ai/prompts/c/marketing)
- [Product prompts](https://orisu.ai/prompts/c/product)
- [Video prompts](https://orisu.ai/prompts/c/video)
- [Search prompts](https://orisu.ai/prompts/search)
- [How the prompt library works](https://orisu.ai/prompts/about): Where prompts come from, credits to creators, and how to request removal

## Solutions

- [UGC-style ads](https://orisu.ai/solutions/ugc-ads): Script, voice and video ad pipelines with AI actors
- [Product ads](https://orisu.ai/solutions/product-ads): One product photo in, an on-brand ad set out
- [Ecommerce video ads](https://orisu.ai/solutions/ecommerce-video-ads): Product photos from a store listing in, video ads in every channel size out
- [DTC creative testing](https://orisu.ai/solutions/dtc-ads): Loop over a list of hooks and test many angles per rerun
- [Ad localization](https://orisu.ai/solutions/ad-localization): Swap the market input and rerun the campaign, dubbed and captioned
- [App install ads](https://orisu.ai/solutions/app-ads): Screenshots and store assets into app install video ads
- [Game ads](https://orisu.ai/solutions/game-ads): Mobile game ad creatives with a consistent hero character
- [Local services ads](https://orisu.ai/solutions/services-ads): Lead-gen video ads for clinics, contractors and salons
- [Real estate ads](https://orisu.ai/solutions/real-estate-ads): Listing photos into a branded video ad
- [Architecture renders](https://orisu.ai/solutions/architecture-renders): Sketches and massing screenshots into styled renders, one look across every view
- [Launch pack](https://orisu.ai/launch-pack): Done for you: your first 10 on-brand ads built in Orisu within 48 hours for $399, generation included; the workflow stays yours, money back if none are usable
- [Black Friday ad pack](https://orisu.ai/bfcm): Free workflow that turns one product page and photo into six Black Friday / Cyber Monday ads
- [Black Friday ad ideas](https://orisu.ai/black-friday-ad-ideas): Twelve Black Friday ad angles for small brands, with real examples and an October to November plan
- [Black Friday ad templates](https://orisu.ai/black-friday-ad-templates): Six BFCM ad formats, sizes per placement, and how to fill them from a product page
- [Cyber Monday ads](https://orisu.ai/cyber-monday-ads): Cyber Monday ad ideas and a Friday to Tuesday schedule
- [For ecommerce](https://orisu.ai/use-cases/ecommerce): Product imagery and ads at catalog scale
- [For agencies](https://orisu.ai/use-cases/agencies): A brand kit per client and reusable pipelines
- [For brand teams](https://orisu.ai/use-cases/brand-teams): On-brand output at volume

## Comparisons

- [Orisu vs Arcads](https://orisu.ai/compare/arcads)
- [Orisu vs Creatify](https://orisu.ai/compare/creatify)
- [Orisu vs AdCreative.ai](https://orisu.ai/compare/adcreative-ai)
- [Orisu vs Flora](https://orisu.ai/compare/flora)
- [Orisu vs Pletor](https://orisu.ai/compare/pletor)
- [Orisu vs Predis.ai](https://orisu.ai/compare/predis-ai)
- [Orisu vs Photoroom](https://orisu.ai/compare/photoroom)

## Documentation

- [Help docs](https://docs.orisu.ai): Product documentation: guides, node reference, API and MCP
- [MCP server](https://docs.orisu.ai/mcp/overview): Connect Orisu to Claude or ChatGPT

## Blog

Topics: On-brand AI · AI workflows · Playbooks · Tools & comparisons
Authors: [Ari Ivogli](https://orisu.ai/blog/authors/ari) (founder) · [Orisu Team](https://orisu.ai/blog/authors/orisu-team) · [Orisu Research](https://orisu.ai/blog/authors/orisu-research)

- [How to build festive campaigns that sell: Halloween to New Year, moment by moment](https://orisu.ai/blog/festive-campaign-playbook): Halloween, Black Friday, Christmas and the moments in between each need a different campaign. The 2026 dates, the five phases every campaign runs through, and how to keep your brand when everything turns red.
- [AI video model pricing for ads (October 2026): cost per second and per 15-second ad](https://orisu.ai/blog/ai-video-model-pricing-for-ads): What 28 AI video model settings cost per second and per 15-second ad, from Seedance 2.5 and Veo 3.1 to Kling 3.0 and Hailuo H3, plus lip-sync and dubbing. Read from Orisu's live catalog.
- [ComfyUI alternatives for marketers: node canvases that don't need a GPU](https://orisu.ai/blog/comfyui-alternatives-for-marketers): The best ComfyUI alternative depends on why you're leaving: the GPU, the setup, or the lack of ad tooling. Comfy Cloud, RunComfy, Flora, Figma Weave, Krea Nodes, Magnific Spaces, Promptus and Orisu compared.
- [Creatify pricing explained (2026): credits, real cost per video, and cheaper ways to get the same ads](https://orisu.ai/blog/creatify-pricing): Creatify pricing in plain numbers: what each plan costs, how many credits a 15, 30 or 60-second ad uses, what the API charges, when credits expire, and when another tool gets you the same ad for less.
- [Figma Weave (formerly Weavy) alternatives in 2026](https://orisu.ai/blog/figma-weave-alternatives): Weavy is now Figma Weave. What changed after Figma's acquisition, what Weave costs today, and the best Weavy alternative for ad production: Flora, Krea Nodes, Magnific Spaces, ComfyUI or Orisu.
- [Higgsfield alternatives for ad teams (2026)](https://orisu.ai/blog/higgsfield-alternatives-for-ad-teams): Looking for a Higgsfield alternative for ad production? Arcads, Creatify, HeyGen, Krea, Flora and Orisu compared on UGC actors, catalog runs, cost per ad and credit expiry, with prices from each vendor's site.
- [Higgsfield MCP alternatives: generate ads from Claude or ChatGPT (2026)](https://orisu.ai/blog/higgsfield-mcp-alternatives): Higgsfield MCP lets Claude and ChatGPT generate images and video on your Higgsfield credits. Here are the hosted MCP alternatives for ad work, compared on auth, billing, cost checks, brand memory and workflows.
- [How much does an AI UGC ad cost? Arcads vs Creatify vs Higgsfield vs HeyGen vs DIY (2026)](https://orisu.ai/blog/how-much-do-ai-ugc-ads-cost): How much do AI UGC ads cost? We priced one 15-second and one 30-second talking-actor ad in Arcads, Creatify, Higgsfield, HeyGen, Orisu and the raw model APIs, using each vendor's own published units.
- [Krea alternatives for ad production (2026)](https://orisu.ai/blog/krea-alternatives-for-ad-production): Krea is great for exploring ideas in realtime. When the job turns into ad production, with actors, catalogs and languages, these Krea alternatives fit better: Higgsfield, Flora, Figma Weave, Magnific Spaces and Orisu.
- [Meta catalog ads with AI: turn your Shopify feed into catalog creative](https://orisu.ai/blog/meta-catalog-ads-with-ai): How to make AI creative for Meta catalog ads from a Shopify feed: what Meta's own AI does, the feed and image specs that matter, TikTok's differences, and a step-by-step run with real costs for 200 products.
- [How to give Claude or ChatGPT a canvas with MCP (step by step)](https://orisu.ai/blog/how-to-give-claude-a-canvas-with-mcp): Add a canvas to Claude or ChatGPT in about two minutes with an MCP connector, pick the right one for the job, and build your own MCP App if nothing fits. Includes setup, troubleshooting, and code.
- [Why give your AI agent a canvas? What changes when Claude or ChatGPT can see the work](https://orisu.ai/blog/why-give-your-ai-agent-a-canvas): Chat is a poor place to hold a plan with ten steps. Here's what a canvas gives Claude, ChatGPT, or your own agent, which tools offer one in 2026, and when plain chat is still enough.
- [Can you use AI-generated content commercially? Licenses, ownership, and indemnity compared](https://orisu.ai/blog/commercial-use-of-ai-generated-content): Three different questions hide inside 'is this AI image safe to use?': license, ownership, and who pays if you get sued. Here's how the major AI providers differ on each, and what it means for brand teams.
- [You can now run Orisu from ChatGPT](https://orisu.ai/blog/connect-chatgpt-to-orisu-mcp): Orisu's MCP connector now works in ChatGPT. Add one URL, sign in, and build and run your content workflows without leaving the chat.
- [What is agentic image generation? Reasoning image models, explained](https://orisu.ai/blog/what-is-agentic-image-generation): In 2026, image models stopped just rendering and started reasoning: searching the web, writing code, and checking their own work. Here's what agentic image generation is and when marketing teams should use it.
- [Seedance 2.5 for ads: what it does, what a 30-second ad costs, and how to prompt it](https://orisu.ai/blog/30-second-ai-video-ads-seedance-2-5): Seedance 2.5 renders a 30-second ad with sound in one take. What changed from 2.0, the real cost per second and per ad at 480p, 720p and 1080p, and a prompt format that holds up for UGC-style spots.
- [How much does AI content generation actually cost? (2026)](https://orisu.ai/blog/how-much-does-ai-content-generation-cost): What AI content generation really costs in 2026: seat vs credit vs API pricing, why video dwarfs images, where the hidden waste hides, and a formula for estimating your own volume.
- [Prompts, voice profiles, or fine-tuning: how to keep AI copy in your brand voice](https://orisu.ai/blog/keep-ai-copy-in-your-brand-voice): AI copy drifts into a generic voice fast. Compare the three ways to hold your brand voice in AI writing (prompt examples, a stored voice profile and fine-tuning) and which to reach for first.
- [How to repurpose webinars into social clips with AI](https://orisu.ai/blog/repurpose-webinars-into-social-clips-with-ai): A 45-minute webinar holds a month of social content. This playbook walks through finding the moments, cutting the clips, captioning, resizing, and shipping them on-brand with AI.
- [7 AI content workflows every marketing team should steal](https://orisu.ai/blog/seven-ai-content-workflows-to-steal): Seven repeatable AI content workflows, from URL-to-ad-variants to one-click weekly drops, with the pipeline shape, who each is for, and how to build it.
- [How to storyboard AI video ads before you spend a credit](https://orisu.ai/blog/how-to-storyboard-ai-video-ads): AI video is too expensive to art-direct by re-rolling. Storyboard with cheap stills first, get sign-off, then animate only the approved frames. A step-by-step playbook.
- [Machine-readable brand guidelines: making your brand legible to AI](https://orisu.ai/blog/machine-readable-brand-guidelines): Your brand guidelines' most frequent reader is now a machine. Here's what machine-readable brand guidelines are, why the PDF fails, and how to translate voice and visual rules into instructions AI can follow.
- [Meta, Google, and TikTok will generate your ads now. Should you let them?](https://orisu.ai/blog/platform-ai-ad-creative-vs-your-own-pipeline): Meta's Muse Image, TikTok Symphony, and Google's asset generation all make ad creative for you. Where platform AI helps, where it flattens your brand, and how to split the work.
- [Best AI video model for ads (2026): Veo 3.1, Kling 3.0, Seedance 2.5 and when to use which](https://orisu.ai/blog/ai-video-models-when-to-use-which): Which AI video model to use for UGC ads, product clips, animating stills, talking heads and cheap hook tests in 2026, with real per-second costs and a simple way to decide when a new model is worth switching to.
- [AI avatar videos for marketing: 7 on-brand use cases (2026)](https://orisu.ai/blog/ai-avatar-videos-for-marketing): A practical roundup of where AI avatar and spokesperson videos earn their keep in marketing, plus the brand and legal lines you should not cross.
- [A full product launch asset set from one URL](https://orisu.ai/blog/product-launch-assets-from-a-url): How to turn one product page URL into a complete launch pack (hero visuals, social announcements, ad variants, an email header, and a short video) in a single pipeline.
- [AI slop: what it is, and how marketing teams avoid it](https://orisu.ai/blog/how-to-avoid-ai-slop-in-marketing): 'Slop' was Merriam-Webster's 2025 word of the year: low-quality AI content made in quantity. Here's why marketing teams produce it, what it costs, and the workflow that prevents it.
- [Reference images, brand kits, or fine-tuning: how to lock AI to your brand](https://orisu.ai/blog/reference-images-vs-brand-kit-vs-fine-tuning): Three ways to make AI generation match your brand: reference images, a structured brand kit, and fine-tuning. How each works, where each breaks, and which to reach for first.
- [AI voiceover for marketing videos: which text-to-speech to use when](https://orisu.ai/blog/ai-voiceover-for-marketing-videos): AI voiceover is good enough for real marketing video now, but the right approach depends on the job. How dedicated TTS, native-audio video, avatar tools, and human voice compare, and when to use each.
- [Multimodal AI pipelines: image, video, text, and audio in one place](https://orisu.ai/blog/multimodal-ai-content-pipelines): Real campaigns need scripts, voiceovers, video, captions, and thumbnails. What changes when all four content types share one pipeline, and when separate tools still win.
- [The Q4 holiday creative playbook: start your AI production line in July](https://orisu.ai/blog/q4-holiday-ai-creative-playbook): Holiday creative eats Q4 teams alive every year. Here's a month-by-month playbook for building an AI production line in July that carries you through Cyber Week.
- [Brand consistency at scale: a playbook for lean teams](https://orisu.ai/blog/brand-consistency-at-scale): More channels, more assets, same two designers. A six-step playbook for keeping everything on-brand when demand outgrows the team.
- [How to review AI content before it ships: a brand-safety checklist](https://orisu.ai/blog/how-to-review-ai-content-before-it-ships): AI lets you make marketing content faster than anyone can check it. Here's a step-by-step review workflow to catch off-brand, false, or non-compliant output before it goes live.
- [AI music for marketing videos: what's safe to use, and how to stay on-brand](https://orisu.ai/blog/ai-music-for-marketing-videos): AI can now write studio-grade music from a text prompt, but not every tool is cleared for commercial use. Here's what AI music is, where it's safe for marketing, and how to keep it on-brand.
- [Structured prompting for AI video: the format behind consistent clips](https://orisu.ai/blog/structured-prompting-for-ai-video): Vague prompts hand you a different video every run. Structured prompting (named components, formulas and JSON) is how marketing teams make AI video output consistent and repeatable enough to ship.
- [Best AI image model for product photos and ads (2026): which model to use when](https://orisu.ai/blog/ai-image-models-when-to-use-which): Which AI image model to use for product photos, text-heavy ads, consistent characters and cheap variants in 2026, with current leaderboard standings, real per-image costs and a five-question way to choose.
- [AI dubbing for ads: localize one winning video ad into 10 languages (cost and lip-sync compared)](https://orisu.ai/blog/ai-ad-localization-at-scale): How to dub a winning video ad into other languages with AI: when you need lip-sync and when a voice track is enough, what each language costs, how the main dubbing tools compare, and the review step you can't skip.
- [Text in AI images: which models can actually spell in 2026](https://orisu.ai/blog/text-in-ai-images-for-marketing): AI image models still garble text by default. Here's why they struggle, which 2026 models render legible type, and the workflow for getting brand names and headlines right.
- [Turn one blog post into a week of social content with AI](https://orisu.ai/blog/blog-post-to-social-content-pack): Stop letting posts die on publish day. A step-by-step AI workflow that turns one blog post into schedule-ready LinkedIn, X, and Instagram content: copy and visuals in your brand voice.
- [Consistent AI characters: how to keep a brand mascot on-model](https://orisu.ai/blog/consistent-ai-characters-for-brand-mascots): AI image models redraw your character every time by default. Here's how consistent-character generation works in 2026, the methods that hold a face steady, and how to keep a brand mascot on-model.
- [AI video with native audio: what it changes for marketing teams](https://orisu.ai/blog/ai-video-with-native-audio): AI video models now generate dialogue, sound effects, and music in the same pass as the picture. Here's what native audio is, why it matters in 2026, and how to use it on-brand.
- [What is MCP? The Model Context Protocol, explained for marketing teams](https://orisu.ai/blog/what-is-mcp-for-marketing-teams): MCP, the Model Context Protocol, is the open standard that lets AI assistants plug into your real tools and data. Here's what it means for marketing teams, and when to use it.
- [AI UGC ads: the honest playbook for on-brand creative at scale](https://orisu.ai/blog/ai-ugc-ads-playbook): AI UGC ads let lean teams test creator-style video at volume. Here's the honest playbook for making them on-brand and keeping them on the right side of the FTC's rules.
- [AI content agents: what they actually do for marketing teams](https://orisu.ai/blog/ai-content-agents-for-marketing-teams): AI content agents don't just generate one asset; they run multi-step content work on their own. Here's what they really do, where they help, and how to keep them on-brand.
- [From prompt to pipeline: making AI content repeatable](https://orisu.ai/blog/from-prompt-to-pipeline): Teams climb the same ladder: one-off prompts, saved prompts, prompt chains, visible pipelines. What breaks at each rung, and the three properties that make AI content actually repeatable.
- [Image-to-video AI: the workflow that keeps your videos on-brand](https://orisu.ai/blog/image-to-video-ai-for-brand-consistency): Text-to-video reinvents your brand on every clip. Image-to-video anchors each generation to a reference image, so your characters and products stay consistent. Here is how it works and when to use it.
- [AI ad disclosure rules 2026: Meta, TikTok, Google, YouTube, the EU AI Act and the FTC](https://orisu.ai/blog/ai-content-disclosure-for-marketing-teams): When AI-generated ads need a label in 2026, who applies it, and what gets an ad rejected, platform by platform: Meta, TikTok, Google Ads, YouTube, EU AI Act Article 50, the FTC and New York. Checked October 6, 2026.
- [Generative engine optimization: how to get your content cited by AI search](https://orisu.ai/blog/generative-engine-optimization-for-marketing-teams): AI search engines answer questions instead of listing links. Here's what actually gets your content cited by ChatGPT, AI Overviews, and Perplexity, plus what Google says to skip.
- [How to keep AI images and video on-brand](https://orisu.ai/blog/keep-ai-images-and-video-on-brand): AI output drifts off-brand by default. A six-step playbook for getting your colors, style, and voice into every image and video you generate.
- [The AI ad variants playbook for performance marketers](https://orisu.ai/blog/ai-ad-variants-playbook): A step-by-step system for turning one approved ad concept into a tested matrix of on-brand variants (hooks, formats, and audiences) without losing your brand along the way.
- [AI creative for agencies: keep every client on-brand](https://orisu.ai/blog/ai-creative-for-agencies): Agencies juggle many brands at once, and AI that drifts off-brand is a client-trust problem. A playbook for per-client brand kits and one reusable pipeline.
- [The best AI image generators for marketing teams (2026)](https://orisu.ai/blog/best-ai-image-generators-for-marketing): Eight AI image generators compared for marketing work (output quality, brand control, team fit, and licensing) from Midjourney to Firefly, plus where a multi-model canvas fits.
- [Best AI video ad generators in 2026: tools compared with real per-ad costs](https://orisu.ai/blog/best-ai-video-tools-for-ads): The best AI video tools for ads in 2026, compared on what a 15-second ad really costs: Veo 3.1, Kling 3.0, Seedance 2.5, Runway, Creatify, Arcads, HeyGen, Higgsfield and Orisu, with each vendor's own published rates.
- [How to build an AI content workflow](https://orisu.ai/blog/how-to-build-an-ai-content-workflow): Chat threads don't scale into production. Here is the full method for building an AI content workflow: define the recurring output, map the steps, add human review, and save it as a graph your team can rerun.
- [Introducing Orisu: the on-brand AI content canvas](https://orisu.ai/blog/introducing-orisu): Orisu is live. Paste your website, get a brand kit, and generate on-brand images, video, text, and audio on one visual canvas, with 100+ models under one subscription.
- [On-brand AI content: the complete guide](https://orisu.ai/blog/on-brand-ai-content-guide): AI can generate anything except your brand, unless you build a system for it. The complete framework: codify, inject, repeat, review, measure.
- [On-brand product imagery for ecommerce, without a studio](https://orisu.ai/blog/on-brand-product-imagery-for-ecommerce): Turn one clean product photo into lifestyle scenes, seasonal variants, and channel sizes that all match your brand, without a studio or a reshoot.
- [What is a visual AI canvas? Nodes, edges, and runs explained](https://orisu.ai/blog/what-is-a-visual-ai-canvas): Nodes, edges, and runs: the three primitives behind every visual AI canvas, how it compares to chat and automation tools, and when a canvas is overkill.
- [What is an AI brand kit?](https://orisu.ai/blog/what-is-an-ai-brand-kit): An AI brand kit is a machine-readable brand system that AI generation reads automatically. Here's how it differs from PDFs, asset folders, and prompt snippets.
- [Why your AI content looks off-brand (and how to fix it)](https://orisu.ai/blog/why-ai-content-looks-off-brand): AI output looks generic because models average the internet and prompts can't carry a brand system. Here's the diagnosis, and the fixes, cheapest first.

## Optional

- [Full blog article text](https://orisu.ai/llms-full.txt): Complete markdown of every published post
- [RSS feed](https://orisu.ai/blog/rss.xml)