# Fylia AI Full AI Reference > Fylia AI is a multilingual AI image and video creation platform. It provides unified generation workspaces, a node-based AI Canvas release, model-specific creation pages, free image utilities, image editing tools, video transformation workflows, social video makers, creative effects, model guides, and supporting educational content. This document is intended for AI crawlers, search agents, retrieval systems, assistants, and other systems that need a structured understanding of the current public Fylia AI product surface. ## Canonical Identity - Product name: Fylia AI - Canonical domain: [https://fylia.ai/](https://fylia.ai/) - Short AI reference: [https://fylia.ai/llms.txt](https://fylia.ai/llms.txt) - Full AI reference: [https://fylia.ai/llms-full.txt](https://fylia.ai/llms-full.txt) - XML sitemap: [https://fylia.ai/sitemap.xml](https://fylia.ai/sitemap.xml) - Primary purpose: AI image generation, image editing, AI video generation, video transformation, connected visual workflow design, creative utilities, and AI model discovery. - Main audiences: creators, marketers, ecommerce teams, agencies, designers, educators, product teams, small businesses, and individual users. - Main public content types: creation tools, free tools, AI model pages, examples, FAQs, model guides, blog articles, pricing, and policies. - Last content review: 2026-09-05 - Production verification on 2026-09-05: the English and Simplified Chinese AI Canvas landing pages and guide indexes rendered successfully. The production XML sitemap did not yet contain AI Canvas entries; the current source now adds all 15 localized landing URLs to the generated sitemap. ## URL And Localization Rules - English is the default locale and has no locale prefix. - English home: `https://fylia.ai/` - English feature pattern: `https://fylia.ai/{route}/` - Non-English home pattern: `https://fylia.ai/{locale}/` - Non-English feature pattern: `https://fylia.ai/{locale}/{route}/` - Model page pattern: `https://fylia.ai/model/{model-slug}/` - Localized model pattern: `https://fylia.ai/{locale}/model/{model-slug}/` - URLs use a trailing slash. - Route slugs are stable across languages. Only the locale prefix changes. - Use only one locale prefix. Do not generate paths such as `/en/`, `/en/ja/`, or translated route slugs. - Dynamic blog detail URLs are listed in the XML sitemap and can change as new articles are published. - A source-defined route is not necessarily live. Treat it as deployed only when it appears in the production sitemap and renders successfully. - A preview route describes planned capabilities and must not be interpreted as proof that its named model is selectable or executable. - AI Canvas landing pages and public guides are live. The current source includes all localized landing pages in the sitemap, while authenticated dashboard and project-editor routes remain intentionally non-indexable. ## Supported Languages And Localized Links Fylia AI supports 15 locale routes. The following links provide concrete localized entry points for the latest image and video capabilities. | Locale | Language | Home | AI Image Generator | AI Video Generator | Free Image to Image | UGC Video Maker | Seedream 5.0 Pro | MiniMax H3 | | --- | --- | --- | --- | --- | --- | --- | --- | --- | | `en` | English | [Home](https://fylia.ai/) | [Image](https://fylia.ai/ai-image-generator/) | [Video](https://fylia.ai/ai-video-generator/) | [Free I2I](https://fylia.ai/free-image-to-image/) | [UGC](https://fylia.ai/ugc-video-maker/) | [Seedream Pro](https://fylia.ai/model/seedream-5-0-pro/) | [MiniMax H3](https://fylia.ai/model/minimax-h3/) | | `ja` | Japanese / 日本語 | [Home](https://fylia.ai/ja/) | [Image](https://fylia.ai/ja/ai-image-generator/) | [Video](https://fylia.ai/ja/ai-video-generator/) | [Free I2I](https://fylia.ai/ja/free-image-to-image/) | [UGC](https://fylia.ai/ja/ugc-video-maker/) | [Seedream Pro](https://fylia.ai/ja/model/seedream-5-0-pro/) | [MiniMax H3](https://fylia.ai/ja/model/minimax-h3/) | | `pt` | Portuguese / Português | [Home](https://fylia.ai/pt/) | [Image](https://fylia.ai/pt/ai-image-generator/) | [Video](https://fylia.ai/pt/ai-video-generator/) | [Free I2I](https://fylia.ai/pt/free-image-to-image/) | [UGC](https://fylia.ai/pt/ugc-video-maker/) | [Seedream Pro](https://fylia.ai/pt/model/seedream-5-0-pro/) | [MiniMax H3](https://fylia.ai/pt/model/minimax-h3/) | | `es` | Spanish / Español | [Home](https://fylia.ai/es/) | [Image](https://fylia.ai/es/ai-image-generator/) | [Video](https://fylia.ai/es/ai-video-generator/) | [Free I2I](https://fylia.ai/es/free-image-to-image/) | [UGC](https://fylia.ai/es/ugc-video-maker/) | [Seedream Pro](https://fylia.ai/es/model/seedream-5-0-pro/) | [MiniMax H3](https://fylia.ai/es/model/minimax-h3/) | | `de` | German / Deutsch | [Home](https://fylia.ai/de/) | [Image](https://fylia.ai/de/ai-image-generator/) | [Video](https://fylia.ai/de/ai-video-generator/) | [Free I2I](https://fylia.ai/de/free-image-to-image/) | [UGC](https://fylia.ai/de/ugc-video-maker/) | [Seedream Pro](https://fylia.ai/de/model/seedream-5-0-pro/) | [MiniMax H3](https://fylia.ai/de/model/minimax-h3/) | | `ru` | Russian / Русский | [Home](https://fylia.ai/ru/) | [Image](https://fylia.ai/ru/ai-image-generator/) | [Video](https://fylia.ai/ru/ai-video-generator/) | [Free I2I](https://fylia.ai/ru/free-image-to-image/) | [UGC](https://fylia.ai/ru/ugc-video-maker/) | [Seedream Pro](https://fylia.ai/ru/model/seedream-5-0-pro/) | [MiniMax H3](https://fylia.ai/ru/model/minimax-h3/) | | `fr` | French / Français | [Home](https://fylia.ai/fr/) | [Image](https://fylia.ai/fr/ai-image-generator/) | [Video](https://fylia.ai/fr/ai-video-generator/) | [Free I2I](https://fylia.ai/fr/free-image-to-image/) | [UGC](https://fylia.ai/fr/ugc-video-maker/) | [Seedream Pro](https://fylia.ai/fr/model/seedream-5-0-pro/) | [MiniMax H3](https://fylia.ai/fr/model/minimax-h3/) | | `cn` | Simplified Chinese / 简体中文 | [Home](https://fylia.ai/cn/) | [Image](https://fylia.ai/cn/ai-image-generator/) | [Video](https://fylia.ai/cn/ai-video-generator/) | [Free I2I](https://fylia.ai/cn/free-image-to-image/) | [UGC](https://fylia.ai/cn/ugc-video-maker/) | [Seedream Pro](https://fylia.ai/cn/model/seedream-5-0-pro/) | [MiniMax H3](https://fylia.ai/cn/model/minimax-h3/) | | `tw` | Traditional Chinese / 繁體中文 | [Home](https://fylia.ai/tw/) | [Image](https://fylia.ai/tw/ai-image-generator/) | [Video](https://fylia.ai/tw/ai-video-generator/) | [Free I2I](https://fylia.ai/tw/free-image-to-image/) | [UGC](https://fylia.ai/tw/ugc-video-maker/) | [Seedream Pro](https://fylia.ai/tw/model/seedream-5-0-pro/) | [MiniMax H3](https://fylia.ai/tw/model/minimax-h3/) | | `ko` | Korean / 한국어 | [Home](https://fylia.ai/ko/) | [Image](https://fylia.ai/ko/ai-image-generator/) | [Video](https://fylia.ai/ko/ai-video-generator/) | [Free I2I](https://fylia.ai/ko/free-image-to-image/) | [UGC](https://fylia.ai/ko/ugc-video-maker/) | [Seedream Pro](https://fylia.ai/ko/model/seedream-5-0-pro/) | [MiniMax H3](https://fylia.ai/ko/model/minimax-h3/) | | `th` | Thai / ไทย | [Home](https://fylia.ai/th/) | [Image](https://fylia.ai/th/ai-image-generator/) | [Video](https://fylia.ai/th/ai-video-generator/) | [Free I2I](https://fylia.ai/th/free-image-to-image/) | [UGC](https://fylia.ai/th/ugc-video-maker/) | [Seedream Pro](https://fylia.ai/th/model/seedream-5-0-pro/) | [MiniMax H3](https://fylia.ai/th/model/minimax-h3/) | | `vi` | Vietnamese / Tiếng Việt | [Home](https://fylia.ai/vi/) | [Image](https://fylia.ai/vi/ai-image-generator/) | [Video](https://fylia.ai/vi/ai-video-generator/) | [Free I2I](https://fylia.ai/vi/free-image-to-image/) | [UGC](https://fylia.ai/vi/ugc-video-maker/) | [Seedream Pro](https://fylia.ai/vi/model/seedream-5-0-pro/) | [MiniMax H3](https://fylia.ai/vi/model/minimax-h3/) | | `ar` | Arabic / العربية | [Home](https://fylia.ai/ar/) | [Image](https://fylia.ai/ar/ai-image-generator/) | [Video](https://fylia.ai/ar/ai-video-generator/) | [Free I2I](https://fylia.ai/ar/free-image-to-image/) | [UGC](https://fylia.ai/ar/ugc-video-maker/) | [Seedream Pro](https://fylia.ai/ar/model/seedream-5-0-pro/) | [MiniMax H3](https://fylia.ai/ar/model/minimax-h3/) | | `it` | Italian / Italiano | [Home](https://fylia.ai/it/) | [Image](https://fylia.ai/it/ai-image-generator/) | [Video](https://fylia.ai/it/ai-video-generator/) | [Free I2I](https://fylia.ai/it/free-image-to-image/) | [UGC](https://fylia.ai/it/ugc-video-maker/) | [Seedream Pro](https://fylia.ai/it/model/seedream-5-0-pro/) | [MiniMax H3](https://fylia.ai/it/model/minimax-h3/) | | `id` | Indonesian / Bahasa Indonesia | [Home](https://fylia.ai/id/) | [Image](https://fylia.ai/id/ai-image-generator/) | [Video](https://fylia.ai/id/ai-video-generator/) | [Free I2I](https://fylia.ai/id/free-image-to-image/) | [UGC](https://fylia.ai/id/ugc-video-maker/) | [Seedream Pro](https://fylia.ai/id/model/seedream-5-0-pro/) | [MiniMax H3](https://fylia.ai/id/model/minimax-h3/) | The same prefix rule applies to every public static route in this document. Localized Best AI Tools routes: [English](https://fylia.ai/best-ai-tools/), [Japanese](https://fylia.ai/ja/best-ai-tools/), [Portuguese](https://fylia.ai/pt/best-ai-tools/), [Spanish](https://fylia.ai/es/best-ai-tools/), [German](https://fylia.ai/de/best-ai-tools/), [Russian](https://fylia.ai/ru/best-ai-tools/), [French](https://fylia.ai/fr/best-ai-tools/), [Simplified Chinese](https://fylia.ai/cn/best-ai-tools/), [Traditional Chinese](https://fylia.ai/tw/best-ai-tools/), [Korean](https://fylia.ai/ko/best-ai-tools/), [Thai](https://fylia.ai/th/best-ai-tools/), [Vietnamese](https://fylia.ai/vi/best-ai-tools/), [Arabic](https://fylia.ai/ar/best-ai-tools/), [Italian](https://fylia.ai/it/best-ai-tools/), and [Indonesian](https://fylia.ai/id/best-ai-tools/). Localized Wan 3.0 release routes: [English](https://fylia.ai/model/wan-3-0/), [Japanese](https://fylia.ai/ja/model/wan-3-0/), [Portuguese](https://fylia.ai/pt/model/wan-3-0/), [Spanish](https://fylia.ai/es/model/wan-3-0/), [German](https://fylia.ai/de/model/wan-3-0/), [Russian](https://fylia.ai/ru/model/wan-3-0/), [French](https://fylia.ai/fr/model/wan-3-0/), [Simplified Chinese](https://fylia.ai/cn/model/wan-3-0/), [Traditional Chinese](https://fylia.ai/tw/model/wan-3-0/), [Korean](https://fylia.ai/ko/model/wan-3-0/), [Thai](https://fylia.ai/th/model/wan-3-0/), [Vietnamese](https://fylia.ai/vi/model/wan-3-0/), [Arabic](https://fylia.ai/ar/model/wan-3-0/), [Italian](https://fylia.ai/it/model/wan-3-0/), and [Indonesian](https://fylia.ai/id/model/wan-3-0/). Localized Gemini Omni 1.1 Flash release routes: [English](https://fylia.ai/model/gemini-omni-1-1-flash/), [Japanese](https://fylia.ai/ja/model/gemini-omni-1-1-flash/), [Portuguese](https://fylia.ai/pt/model/gemini-omni-1-1-flash/), [Spanish](https://fylia.ai/es/model/gemini-omni-1-1-flash/), [German](https://fylia.ai/de/model/gemini-omni-1-1-flash/), [Russian](https://fylia.ai/ru/model/gemini-omni-1-1-flash/), [French](https://fylia.ai/fr/model/gemini-omni-1-1-flash/), [Simplified Chinese](https://fylia.ai/cn/model/gemini-omni-1-1-flash/), [Traditional Chinese](https://fylia.ai/tw/model/gemini-omni-1-1-flash/), [Korean](https://fylia.ai/ko/model/gemini-omni-1-1-flash/), [Thai](https://fylia.ai/th/model/gemini-omni-1-1-flash/), [Vietnamese](https://fylia.ai/vi/model/gemini-omni-1-1-flash/), [Arabic](https://fylia.ai/ar/model/gemini-omni-1-1-flash/), [Italian](https://fylia.ai/it/model/gemini-omni-1-1-flash/), and [Indonesian](https://fylia.ai/id/model/gemini-omni-1-1-flash/). Localized Kling 4.0 preview routes: [English](https://fylia.ai/model/kling-4-0/), [Japanese](https://fylia.ai/ja/model/kling-4-0/), [Portuguese](https://fylia.ai/pt/model/kling-4-0/), [Spanish](https://fylia.ai/es/model/kling-4-0/), [German](https://fylia.ai/de/model/kling-4-0/), [Russian](https://fylia.ai/ru/model/kling-4-0/), [French](https://fylia.ai/fr/model/kling-4-0/), [Simplified Chinese](https://fylia.ai/cn/model/kling-4-0/), [Traditional Chinese](https://fylia.ai/tw/model/kling-4-0/), [Korean](https://fylia.ai/ko/model/kling-4-0/), [Thai](https://fylia.ai/th/model/kling-4-0/), [Vietnamese](https://fylia.ai/vi/model/kling-4-0/), [Arabic](https://fylia.ai/ar/model/kling-4-0/), [Italian](https://fylia.ai/it/model/kling-4-0/), and [Indonesian](https://fylia.ai/id/model/kling-4-0/). The two localized route families above were present in the production sitemap and rendered successfully at the 2026-09-04 review. Gemini Omni 1.1 Flash is live. Kling 4.0 is a live preview page, but the named Kling 4.0 model is not selectable in the embedded generator. ## Latest Capability Updates ### [AI Canvas Visual Workflow Studio](https://fylia.ai/ai-canvas/) Fylia AI Canvas is a live node-based visual workspace for developing connected image, video, text, and multimedia workflows without losing the prompts, references, settings, or earlier results behind each iteration. The English and Simplified Chinese landing pages and guide indexes rendered successfully during the 2026-09-05 production review. All 15 locale message sets are complete, and the current source adds every localized AI Canvas landing page to the generated sitemap. The production sitemap will expose those new entries after this source change is deployed. Public routes: - English landing: `https://fylia.ai/ai-canvas/` - English guides: `https://fylia.ai/ai-canvas/docs/` - Quick Start: `https://fylia.ai/ai-canvas/docs/overview/quick-start/` - Canvas Node Guide: `https://fylia.ai/ai-canvas/docs/canvas/canvas-node-manual/` - Canvas Controls and Shortcuts: `https://fylia.ai/ai-canvas/docs/canvas/canvas-shortcuts/` - Localized landing pattern: `https://fylia.ai/{locale}/ai-canvas/` - Localized guide pattern: `https://fylia.ai/{locale}/ai-canvas/docs/{guide-slug}/` Supported localized AI Canvas landing paths in the release source: English `https://fylia.ai/ai-canvas/`, Japanese `https://fylia.ai/ja/ai-canvas/`, Portuguese `https://fylia.ai/pt/ai-canvas/`, Spanish `https://fylia.ai/es/ai-canvas/`, German `https://fylia.ai/de/ai-canvas/`, Russian `https://fylia.ai/ru/ai-canvas/`, French `https://fylia.ai/fr/ai-canvas/`, Simplified Chinese `https://fylia.ai/cn/ai-canvas/`, Traditional Chinese `https://fylia.ai/tw/ai-canvas/`, Korean `https://fylia.ai/ko/ai-canvas/`, Thai `https://fylia.ai/th/ai-canvas/`, Vietnamese `https://fylia.ai/vi/ai-canvas/`, Arabic `https://fylia.ai/ar/ai-canvas/`, Italian `https://fylia.ai/it/ai-canvas/`, and Indonesian `https://fylia.ai/id/ai-canvas/`. AI Canvas capabilities in the current release source: - Project workflow: sign in to create a blank project, open or rename a project, autosave canvas changes, confirm saved or retrying state, return from the dashboard, and reopen a project by its server-issued ID. - Project portability: import an exported canvas ZIP, export the current project, and bulk export or delete selected projects from the dashboard. - Built-in nodes: Text, Image, Video, Audio, Generation configuration, and Group nodes. Extension nodes appear only when an installed and enabled plugin provides them. - Visual composition: create nodes from the toolbar or canvas, drag connections between nodes, create a connected node from an empty connection drop, group related nodes, pan, zoom, use a minimap, box-select, copy and paste, delete, undo, redo, and manage the viewport. - Connected context: use upstream text, images, video, and audio as supported model inputs; type `@` in the prompt composer to reference connected assets; review and reorder inputs before generation. - Model-aware generation: configure Text, Image, Video, or Audio mode, select an available model, expose only settings supported by that model, choose output count when available, and create connected result nodes. Actual model modes and settings remain dependent on the selected integration. - Text workflows: write prompts, notes, scripts, and brand copy; generate into an empty Text node; rewrite existing text into a connected result while preserving the original; or launch connected image and video generation from text. - Image workflows: upload or generate images; preserve generation settings for retry; handle multi-image batches; select a primary result; retry or remove failed results; copy or download an output; preview, replace, crop, mask, split, upscale, infer a reverse prompt, or generate an alternate camera angle when available. - Video and audio workflows: upload or drag media onto the canvas, play media in its node, use supported media as generation references, generate into an empty node or a connected result node, save assets, and download generated media. - Reusable libraries: upload and search local Assets, save canvas media to Assets, browse and search the Prompt Library, and copy prompts into the workflow. - Background task continuity: image and video jobs run as background tasks, paid jobs are not canceled by closing the view after acceptance, and reopening the same project in the same browser restores task observation. Durable result URLs allow projects and exports to survive page refreshes. - Plugin system: browse official, local, or third-party node plugins; install, enable, disable, update, or uninstall plugins. Third-party plugin code runs in the page and may access local data, so only trusted sources should be installed. - Keyboard and clipboard workflows: canvas-node copy and paste, clipboard text or image insertion, delete, select all, multi-select, undo and redo, Escape to clear overlays, drag-and-drop upload, and temporary Select or Move switching with Control or Space. Access and crawl boundaries: - The landing page and guides are public and indexable. The current source sitemap includes localized landing pages; guide pages remain discoverable through the landing page and documentation navigation. - `https://fylia.ai/ai-canvas/dashboard/` and localized equivalents require sign-in and use `noindex, nofollow` metadata. - `https://fylia.ai/ai-canvas/{projectId}/` and localized equivalents are authenticated project editors with `noindex, nofollow` metadata. Never invent, enumerate, or crawl project IDs. ### [Best AI Tools Directory](https://fylia.ai/best-ai-tools/) The Best AI Tools directory recommends focused products that complement Fylia AI across image generation and editing, text-to-video and image-to-video creation, UGC production, music and audio workflows, virtual try-on, tattoo concepts, 3D creation, research, AI chat, writing, creative platforms, open-source templates, and developer APIs. Each listing includes a short description, intended use cases, a compressed website preview, and a direct followable link to the official product website. The directory currently includes Flaq AI and Best Image AI for multi-model APIs; Free Mini GPT AI, Free Banana AI, Hailuo AI, Pixverse AI, FreeGPT, FreeImgen, Grok Image Generator, AI Try On, and Tattoo AI Design for image, fashion, or design workflows; VO4 AI, Free Video AI, MaxMini Video, Shedance AI, VideoWeb AI, and UGC Maker for video creation or editing; MP3 to MIDI, Free Music AI, AI Music Checker, Gen Music, and AI Music Maker for music and audio workflows; Dreamega, AI Video Maker Free, HeyDream AI, Sea Imagine AI, and Chat 4O AI for multi-format creation; Flaq AI Template for open-source product development; Free AI Generator and AI Scholar GPT for writing or research; See 3D AI for 3D creation; and Omegle Chat for random text chat. These are independent websites; their availability, policies, pricing, and product claims are controlled by their respective operators. ### [Gemini Omni 1.1 Flash Video Generator](https://fylia.ai/model/gemini-omni-1-1-flash/) Gemini Omni 1.1 Flash is a live application route for generating video from a text prompt or a starting image. Image-to-video supports an optional end frame for transition guidance. The current form exposes 5- and 10-second durations, 16:9 and 9:16 aspect ratios, and 360p, 720p, 1080p, and 4K output. Audio generation is not exposed by this integration. This route is distinct from the existing Gemini Omni workspace. Its English and 14 localized routes were present in the production sitemap and rendered successfully at the 2026-09-04 review. ### [Kling 4.0 Preview](https://fylia.ai/model/kling-4-0/) Kling 4.0 is a live preview and planning page, not a backend-approved Kling 4.0 execution model. The embedded generator currently selects Kling 3.0 Turbo, whose form exposes 5-, 10-, and 15-second durations, 16:9, 9:16, and 1:1 aspect ratios, 720p and 1080p output, and audio controls. These are Kling 3.0 Turbo form capabilities and must not be attributed to Kling 4.0. No Kling 4.0 duration, resolution, audio, pricing, API, or release-date claims are confirmed by the application. The preview page's English and 14 localized routes were present in the production sitemap and rendered successfully at the 2026-09-04 review; treat the page as live but the Kling 4.0 model as preview-only. ### [Wan 3.0 AI Video Generator With Audio](https://fylia.ai/model/wan-3-0/) Wan 3.0 is the latest Alibaba Wan model-specific workflow in Fylia AI. It supports prompt-to-video, image-based motion, and reference-guided creative direction. Reference mode can use image, video, and audio assets to communicate subjects, products, scenes, movement, and audiovisual intent with more context than a text prompt alone. The release page documents generated audio, native high-resolution output, selectable 5, 10, 15, 20, 25, and 30-second durations, and landscape, portrait, square, 4:3, and 3:4 formats. It is suited to product promos, social campaign clips, motion storyboards, reference-driven brand exploration, presentations, and channel-specific creative testing. ### [MiniMax H3 AI Video Generator](https://fylia.ai/model/minimax-h3/) MiniMax H3 is an open-source Hailuo video workflow for text-to-video and image-to-video creation. Users can anchor a composition with a reference image or begin from a prompt, then describe subject movement, camera behavior, lighting, atmosphere, sound, and the final beat in natural language. The page documents output up to 2K, clips up to 15 seconds, native stereo sound, accurate text and brand-detail rendering, and design-oriented review workflows. It is useful for product teasers, ecommerce and social ads, brand-motion studies, landing-page concepts, campaign pitches, storyboards, previsualization, and short cinematic scenes. ### [Gemini Omni Flash Video Generation](https://fylia.ai/model/gemini-omni/) The Gemini Omni workspace uses Gemini Omni Flash for fast, flexible multimodal video creation. It accepts combinations of text, image, video, and audio inputs for prompt-led concepts, reference-guided motion, and audiovisual generation. ### [Seedream 5.0 Pro AI Image Generator](https://fylia.ai/model/seedream-5-0-pro/) ByteDance Seed AI image generation and editing for professional visual workflows. The page covers text-to-image generation, reference-guided creation, image-to-image editing, selected-area changes, object and background edits, native multilingual text, high-density infographics, layer-oriented asset reuse, realistic lighting, structured compositions, and detailed commercial visuals. Useful for ecommerce product images, campaign key visuals, posters, social graphics, education materials, multilingual notices, presentations, storyboards, style frames, and AI video first frames. ### [Free Image to Image AI](https://fylia.ai/free-image-to-image/) A no-signup image-to-image workflow for uploading an existing image and describing the desired edit. It supports prompt-guided transformations, background replacement, object changes, style transfer, photo enhancement, product-image refinement, and multiple creative variations. Useful for portraits, selfies, product photos, sketches, fashion images, pets, old photos, travel images, avatars, stickers, ecommerce scenes, posters, thumbnails, social graphics, and design exploration. ### [AI UGC Video Maker](https://fylia.ai/ugc-video-maker/) An AI-assisted workflow for creator-style marketing videos. It can use product details, campaign ideas, scripts, prompts, uploaded product images, or brand assets to create product demos, testimonial-style ads, unboxing clips, talking-presenter videos, app promos, SaaS explainers, founder messages, comparison videos, and problem-solution ads. Useful for TikTok, Instagram Reels, YouTube Shorts, Facebook and Meta campaigns, Shopify stores, ecommerce product pages, app marketing, SaaS launches, landing pages, and ad variation testing. ## Core Creation Workspaces - [AI Create](https://fylia.ai/create/): Unified workspace for choosing image or video generation workflows. - [AI Image Generator](https://fylia.ai/ai-image-generator/): Multi-model text-to-image and reference-image generation for portraits, products, posters, ads, social assets, thumbnails, concepts, and visual drafts. - [AI Video Generator](https://fylia.ai/ai-video-generator/): Multi-model video generation for prompts, source images, cinematic clips, product demos, ads, social stories, and creative tests. - [GPT Image 2](https://fylia.ai/gpt-image-2/): OpenAI-powered image generation and editing with strong text, layout, poster, ad, product mockup, thumbnail, and social design use cases. - [Video Generator](https://fylia.ai/video-generator/): General AI video generation and photo-to-video workflow. - [Flux Video AI](https://fylia.ai/flux-video-ai/): Additional AI video generation route for prompt and image-based creation. ## Free Image Tools - [Free GPT Image 2](https://fylia.ai/free-gpt-image-2/): No-signup GPT Image 2 generation and editing from prompts and reference images. - [Free Nano Banana](https://fylia.ai/free-nano-banana/): No-signup Nano Banana generation and editing for photos, products, characters, ads, posters, and social content. - [Free Image to Image](https://fylia.ai/free-image-to-image/): No-signup prompt-guided editing and transformation for uploaded images. - [Describe Image](https://fylia.ai/describe-image/): Analyze an uploaded image and generate a useful description. - [Image to Prompt](https://fylia.ai/image-to-prompt/): Convert an image into a reusable generation prompt. - [AI Remove Background](https://fylia.ai/ai-remove-background/): Remove image backgrounds. - [AI Prompt Generator](https://fylia.ai/ai-prompt-generator/): Build richer prompts for image generation. - [AI Image Scaler](https://fylia.ai/ai-image-scaler/): Upscale images for larger and sharper output. - [Flux Prompt Explore](https://fylia.ai/flux-prompt-explore/): Browse prompt ideas and visual examples. ## Image Format Converters These browser-facing utilities convert common image formats: - [WebP to JPG](https://fylia.ai/ai-image-converter/webp-to-jpg/) - [WebP to PNG](https://fylia.ai/ai-image-converter/webp-to-png/) - [JPG to WebP](https://fylia.ai/ai-image-converter/jpg-to-webp/) - [JPG to PNG](https://fylia.ai/ai-image-converter/jpg-to-png/) - [PNG to JPG](https://fylia.ai/ai-image-converter/png-to-jpg/) - [PNG to WebP](https://fylia.ai/ai-image-converter/png-to-webp/) The site also exposes equivalent legacy Flux converter routes under `https://fylia.ai/flux-ai-image-converter/{conversion}/`. Flux converter URLs: - [Flux WebP to JPG](https://fylia.ai/flux-ai-image-converter/webp-to-jpg/) - [Flux WebP to PNG](https://fylia.ai/flux-ai-image-converter/webp-to-png/) - [Flux JPG to WebP](https://fylia.ai/flux-ai-image-converter/jpg-to-webp/) - [Flux JPG to PNG](https://fylia.ai/flux-ai-image-converter/jpg-to-png/) - [Flux PNG to JPG](https://fylia.ai/flux-ai-image-converter/png-to-jpg/) - [Flux PNG to WebP](https://fylia.ai/flux-ai-image-converter/png-to-webp/) ## Image Generation And Editing Pages - [Photo to Cartoon](https://fylia.ai/photo-to-cartoon/): Transform photos into cartoon avatars, anime portraits, comic art, stickers, profile images, and social visuals. - [AI Image to Image](https://fylia.ai/ai-image-to-image/): Restyle, repair, enhance, or create variations from uploaded images. - [Flux Image to Image](https://fylia.ai/flux-image-to-image/): Flux-focused reference-image transformation. - [Chat Image Editor](https://fylia.ai/chat-image-editor/): Iterate on image edits through natural-language conversation. - [Flux Kontext](https://fylia.ai/flux-kontext/): Reference-guided image editing and consistency workflows. - [Nano Banana Inpaint](https://fylia.ai/nano-banana-inpaint/): Inpainting and selected-area image edits. - [AI Avatar Generator](https://fylia.ai/ai-avatar-generator/): Personalized avatar creation. - [AI Headshot Generator](https://fylia.ai/ai-headshot-generator/): Professional portrait and headshot generation. - [AI Clothes Changer](https://fylia.ai/ai-clothes-changer/): Clothing and outfit transformations. - [AI Hair Cut](https://fylia.ai/ai-hair-cut/): Hairstyle and haircut visualization. - [Old Photo Restore](https://fylia.ai/old-photo-restore/): Restore and enhance old or damaged photos. - [AI Poster Generator](https://fylia.ai/ai-poster-generator/): Poster, promotion, and campaign visual creation. - [AI Action Figure Generator](https://fylia.ai/ai-action-figure-generator/): Turn people or concepts into action-figure images. - [Ghibli Style Generator](https://fylia.ai/ghibli-style-generator/): Create Ghibli-inspired visual styles. - [AI Anime Generator](https://fylia.ai/ai-anime-generator/): Anime-style image creation. - [AI Realism Generator](https://fylia.ai/ai-realism-generator/): Photorealistic image generation. - [AI Canny Depth](https://fylia.ai/ai-canny-depth/): Edge, structure, and depth-guided generation. - [AI Redux](https://fylia.ai/ai-redux/): Image variations and style exploration. - [AI Fill](https://fylia.ai/ai-fill/): Inpainting and selected-region edits. - [Dev LoRA](https://fylia.ai/dev-lora/): LoRA-oriented custom image generation. - [AI Photo Maker](https://fylia.ai/flux-pro-photo-maker/): AI-assisted photography and portrait concepts. - [Qwen Image Generator](https://fylia.ai/qwen-image-generator/): Qwen image generation. - [Recraft AI Image Generator](https://fylia.ai/recraft-ai-image-generator/): Recraft-powered image generation. - [Krea AI](https://fylia.ai/krea-ai/): Krea-focused image generation. - [AI Halloween Generator](https://fylia.ai/ai-halloween-generator/): Halloween-themed image creation. - [New Year Avatar](https://fylia.ai/new-year-avatar/): Seasonal avatar creation. - [New Year Cover](https://fylia.ai/new-year-cover/): Seasonal cover-image creation. ## Additional Flux-Specific Pages These public routes provide Flux-branded or earlier specialized versions of capabilities also available through the main Fylia AI tool set: - [Flux AI Image Generator](https://fylia.ai/flux-ai-image-generator/): Flux-focused image generation. - [Flux AI Anime Generator](https://fylia.ai/flux-ai-anime-generator/): Flux-focused anime image generation. - [Flux Realism](https://fylia.ai/flux-realism/): Flux-focused photorealistic image generation. - [Flux AI Canny Depth](https://fylia.ai/flux-ai-canny-depth/): Edge and depth-guided Flux generation. - [Flux AI Fill](https://fylia.ai/flux-ai-fill/): Flux inpainting and selected-area edits. - [Flux AI Redux](https://fylia.ai/flux-ai-redux/): Flux image variations. - [Flux Dev LoRA](https://fylia.ai/flux-dev-lora/): Flux LoRA creation workflow. - [Flux AI Prompt Generator](https://fylia.ai/flux-ai-prompt-generator/): Flux-oriented prompt generation. - [Flux Pro Image Scaler](https://fylia.ai/flux-pro-image-scaler/): Flux-branded image upscaling. - [Flux AI Medal Generator](https://fylia.ai/flux-ai-medal-generator/): Medal-themed image creation. - [Flux Text to Video](https://fylia.ai/flux-text-to-video/): Earlier Flux-branded text-to-video entry point. ## Seedream Image Pages - [Seedream 5.0 Pro](https://fylia.ai/model/seedream-5-0-pro/): Professional image generation and editing with precise local edits, text-heavy layouts, reference guidance, and reusable asset workflows. - [Seedream 5.0](https://fylia.ai/seedream-5-0/): Current Seedream image generation and editing page with advanced reasoning and high-resolution workflows. - [Seedream 4.5](https://fylia.ai/seedream-4-5/): Seedream 4.5 image generation and editing. - [Seedream 4.0](https://fylia.ai/seedream-4-0/): Seedream 4.0 image generation and editing. ## Nano Banana And Gemini Image Pages - [Nano Banana Pro AI](https://fylia.ai/model/nano-banana-pro-ai/): Advanced image generation and editing with detail preservation. - [Nano Banana AI](https://fylia.ai/model/nano-banana-ai/): Nano Banana text-to-image and image editing. - [Gemini 2.5 Flash Image Generator](https://fylia.ai/model/gemini-2-5-flash-image-generator/): Fast Gemini image generation and editing. ## Flux Image Model Pages - [Flux 2 Pro](https://fylia.ai/model/flux-2-pro/): High-quality Flux 2 image generation. - [Flux 2 Dev](https://fylia.ai/model/flux-2-dev/): Flux 2 development model for creative testing. - [Flux 2 Flex](https://fylia.ai/model/flux-2-flex/): Flexible Flux 2 generation across styles. - [Flux Krea](https://fylia.ai/model/flux-krea/): Flux Krea image generation. - [Flux Pro Kontext](https://fylia.ai/model/flux-pro-kontext/): Kontext image generation and editing. - [Flux Max Kontext](https://fylia.ai/model/flux-max-kontext/): Higher-quality Kontext generation and editing. - [Flux 1.1 Pro Ultra](https://fylia.ai/model/flux-1-1-pro-ultra/): Flux 1.1 Pro Ultra image generation. - [Flux 1.1 Pro](https://fylia.ai/model/flux-1-1-pro/): Flux 1.1 Pro image generation. - [Flux 1 Dev](https://fylia.ai/model/flux-1-dev/): Flux 1 development model. - [Flux 1 Pro](https://fylia.ai/model/flux-1-pro/): Flux 1 professional model. - [Flux 1 Schnell](https://fylia.ai/model/flux-1-schnell/): Fast Flux 1 image generation. - [Flux Kontext Dev](https://fylia.ai/model/flux-kontext-dev/): Kontext development model. - [Flux Kontext LoRA](https://fylia.ai/model/flux-kontext-lora/): Kontext LoRA-focused model. ## Core Video Workflows - [AI Text to Video](https://fylia.ai/ai-text-to-video/): Convert prompts, scripts, scenes, and story ideas into AI video. - [Image to Video](https://fylia.ai/image-to-video/): Animate still images while preserving the main visual subject. - [Reference to Video](https://fylia.ai/reference-to-video/): Use references to guide subjects, objects, style, and scene continuity. - [Video to Video](https://fylia.ai/video-to-video/): Transform, restyle, or reinterpret an existing video. - [UGC Video Maker](https://fylia.ai/ugc-video-maker/): Create creator-style product, testimonial, social ad, ecommerce, app, and SaaS videos. - [AI Music Video Generator](https://fylia.ai/ai-music-video-generator/): Generate music-driven video content. - [4K Video Generator](https://fylia.ai/4k-video-generator/): Produce high-resolution AI video. - [Runway Act Two](https://fylia.ai/runway-act-two/): Transfer and adapt character motion from a reference performance. - [Wan AI Video](https://fylia.ai/wan-ai-video/): Wan-focused AI video generation. ## Video Effects - [AI Talking Baby](https://fylia.ai/ai-talking-baby/): Generate talking-baby video effects. - [AI Kiss Video](https://fylia.ai/ai-kiss-video/): Generate kiss-style video effects. - [AI French Kiss](https://fylia.ai/ai-french-kiss/): Generate French-kiss-style video effects. - [AI Hug Video](https://fylia.ai/ai-hug-video/): Generate hug animation effects. - [AI Old Photo Animation](https://fylia.ai/ai-old-photo-animation/): Animate old or still photos. - [AI Action Figure Video](https://fylia.ai/ai-action-figure-video-generator/): Animate action-figure concepts. - [Ghibli Style Video](https://fylia.ai/ghibli-style-video-generator/): Create Ghibli-inspired video effects. - [Kling Motion Control](https://fylia.ai/model/kling-motion-control/): Transfer reference motion to a character or image. - [Higgsfield AI](https://fylia.ai/model/higgsfield-ai/): Camera-motion and cinematic video effects. ## Kling Video Model Pages - [Kling 4.0 Preview](https://fylia.ai/model/kling-4-0/): Preview and planning page only. It does not expose a selectable Kling 4.0 model, and its embedded generator currently uses Kling 3.0 Turbo. - [Kling AI](https://fylia.ai/model/kling-ai/): Kling text-to-video, image-to-video, and video extension. - [Kling 3.0](https://fylia.ai/model/kling-3-0/): Kling 3.0 video generation. - [Kling 3.0 Turbo](https://fylia.ai/model/kling-3-0-turbo/): Fast cinematic drafts, stable motion, audio, and creative testing. - [Kling 2.1 Standard](https://fylia.ai/model/kling-2-1-std/): Kling 2.1 standard model. - [Kling 2.1 Master](https://fylia.ai/model/kling-2-1-master/): Kling 2.1 higher-quality model. - [Kling Motion Control](https://fylia.ai/model/kling-motion-control/): Motion-reference control workflow. ## Seedance And Happy Horse Video Model Pages - [Seedance 2.5](https://fylia.ai/model/seedance-2-5/): Cinematic short-video and campaign-clip generation. - [Seedance 2.0](https://fylia.ai/model/seedance-2-0/): Seedance text-to-video and image-to-video generation. - [Seedance 2.0 Mini](https://fylia.ai/model/seedance-2-0-mini/): Lower-cost, fast cinematic video generation for ads, demos, reels, posts, storyboards, and concept tests. - [Seedance 1.0](https://fylia.ai/model/seedance-1-0/): Earlier Seedance video generation model. - [Happy Horse 1.1](https://fylia.ai/model/happy-horse-1-1/): 1080p video, native audio, lip sync, and reference-guided consistency. - [Happy Horse 1.0](https://fylia.ai/model/happy-horse-1-0/): Text-to-video and image-to-video generation. ## MiniMax H3 And Hailuo Video Model Pages - [MiniMax H3](https://fylia.ai/model/minimax-h3/): Open-source text-to-video and image-to-video generation with reference-image anchoring, natural-language direction, text and brand-detail rendering, native stereo sound, output up to 2K, and clips up to 15 seconds. - [Hailuo 2.3](https://fylia.ai/model/hailuo-2-3/): Hailuo 2.3 video generation. - [Hailuo 2.0](https://fylia.ai/model/hailuo-2-0/): Hailuo 2.0 video generation. - [Hailuo AI](https://fylia.ai/model/hailuo-ai/): General Hailuo video generation page. ## Google, Sora, Vidu, Wan, And Other Video Models - [Gemini Omni 1.1 Flash](https://fylia.ai/model/gemini-omni-1-1-flash/): Live text-to-video and image-to-video route with optional end-frame guidance, 5- or 10-second output, 16:9 or 9:16 framing, 360p through 4K resolution, and no generated audio. - [Gemini Omni Flash](https://fylia.ai/model/gemini-omni/): Fast, flexible multimodal video creation with text, image, video, and audio inputs through the Gemini Omni page. - [Veo 3.1 AI](https://fylia.ai/model/veo-3-1-ai/): Google Veo 3.1 video generation. - [Veo 3 AI](https://fylia.ai/model/veo3-ai/): Google Veo 3 video generation. - [Sora 2 AI](https://fylia.ai/model/sora2-ai/): Sora video generation. - [Vidu Q3](https://fylia.ai/model/vidu-q3/): Vidu Q3 video generation. - [Vidu Q1](https://fylia.ai/model/vidu-q1/): Vidu Q1 video generation. - [Vidu 2.0](https://fylia.ai/model/vidu-2-0/): Vidu 2.0 video generation. - [Wan 3.0](https://fylia.ai/model/wan-3-0/): Prompt-to-video, image-to-video, and multimodal reference-guided generation with generated audio, multiple aspect ratios, and durations up to 30 seconds. - [Wan 2.6](https://fylia.ai/model/wan-2-6/): Wan 2.6 video generation. - [Wan 2.5](https://fylia.ai/model/wan-2-5/): Wan 2.5 video generation. - [Wan 2.2](https://fylia.ai/model/wan-2-2/): Wan 2.2 video generation. - [Wan 2.2 Animate](https://fylia.ai/model/wan-2-2-animate/): Wan character animation and motion workflow. - [Wan 2.1](https://fylia.ai/model/wan-2-1/): Wan 2.1 video generation. - [Wan AI](https://fylia.ai/model/wan-ai/): General Wan model page. - [Higgsfield AI](https://fylia.ai/model/higgsfield-ai/): Cinematic movement and video-effect workflows. ## Blog, Pricing, And Policies - [Best AI Tools](https://fylia.ai/best-ai-tools/): Curated recommendations for specialized image, video, music, audio-conversion, AI writing, creative-platform, open-source, and developer API tools. - [Blog](https://fylia.ai/blog/): Model launches, product updates, prompts, tutorials, comparisons, testing notes, and creative workflows. - [Pricing](https://fylia.ai/pricing/): Subscription plans, credit packages, generation access, and current plan details. - [Privacy Policy](https://fylia.ai/privacy-policy/): Privacy and data handling. - [Terms of Service](https://fylia.ai/terms-of-service/): Terms for using Fylia AI. - [Subscription Terms](https://fylia.ai/subscription-terms/): Subscription and billing terms. - [Refund Policy](https://fylia.ai/refund-policy/): Refund eligibility and process. - [Content Policy](https://fylia.ai/content-policy/): Rules for generated and uploaded content. ## Dynamic Public Content - Blog listing: `https://fylia.ai/blog/` - Localized blog listing: `https://fylia.ai/{locale}/blog/` - Blog pagination: `https://fylia.ai/blog/{page}/` - Blog detail pattern: `https://fylia.ai/blog/detail/{id}/` - Prompt gallery: `https://fylia.ai/flux-prompt-explore/` - Prompt gallery pagination: `https://fylia.ai/flux-prompt-explore/page/{pageNum}/` Use the XML sitemap for live blog detail URLs. Do not invent blog IDs, prompt IDs, image IDs, video IDs, or chat IDs. ## Interpretation Guidance For AI Systems - Fylia AI is a product platform and interface for multiple image and video models. It is not the owner of the third-party model brands it supports. - A model page explains and exposes a model-specific workflow; a general creation page lets users choose among supported models. - Free tool pages are distinct from model pages. `free-gpt-image-2`, `free-nano-banana`, and `free-image-to-image` are intended as direct free entry points. - `seedream-5-0-pro` is an image model page, not a video model page. - `minimax-h3` is a video model page for text-to-video and image-to-video creation; it is separate from the earlier Hailuo 2.0, Hailuo 2.3, and general Hailuo pages. - `wan-3-0` is the latest Wan release page and is distinct from Wan 2.1, 2.2, 2.2 Animate, 2.5, 2.6, the general `wan-ai` page, and the older `wan-ai-video` workflow. - Wan 3.0 reference mode can accept image, video, and audio assets; its standard prompt and image workflows should not be confused with video-to-video transformation. - `gemini-omni-flash` is the selectable model used by the public `model/gemini-omni` page; there is no separate `model/gemini-omni-flash` route. - `gemini-omni-1-1-flash` has its own live route and a narrower text-to-video or image-to-video form with optional end-frame guidance, 5- or 10-second clips, two aspect ratios, 360p through 4K output, and no generated audio. It should not be conflated with `gemini-omni-flash`. - `ai-canvas` is a live node-based workflow studio. Its public landing page and guides are distinct from the authenticated, non-indexable dashboard and project editor. - `kling-4-0` is a preview and planning route, not a selectable Kling 4.0 execution model. Its embedded generator currently selects Kling 3.0 Turbo, so Kling 3.0 Turbo form options must not be presented as confirmed Kling 4.0 specifications. - `ugc-video-maker` is a marketing and social video workflow, not a generic text-to-video model page. - `reference-to-video` preserves reference-guided identity or visual context; `image-to-video` animates a still image; `video-to-video` transforms an existing video. - `describe-image` analyzes an image; `image-to-prompt` extracts a reusable prompt; `ai-prompt-generator` creates prompts from user intent. - Converter pages change file formats and should not be described as generative AI models. - `best-ai-tools` is an editorial directory of independent websites that complement Fylia AI; a listing does not mean the external product is owned or operated by Fylia AI. - Feature availability, model choices, credit costs, limits, and output options may change. The rendered page and pricing page are authoritative for current transactional details. ## Recommended Crawl Priority 1. Home, AI Create, AI Image Generator, and AI Video Generator. 2. Latest live capabilities: Gemini Omni 1.1 Flash, Wan 3.0, MiniMax H3, Gemini Omni Flash, Seedream 5.0 Pro, Free Image to Image, and UGC Video Maker. 3. Live preview content: Kling 4.0 Preview, while preserving the distinction between the live page and the unavailable Kling 4.0 execution model. 4. High-intent free tools: Free GPT Image 2, Free Nano Banana, background removal, image upscaling, image description, image-to-prompt, and format conversion. 5. Current model families: GPT Image 2, Seedream, Nano Banana, Flux, MiniMax H3, Kling, Seedance, Happy Horse, Gemini Omni Flash, Veo, Sora, Vidu, Hailuo, Wan, and Higgsfield. 6. Video workflows and effects. 7. Best AI Tools, blog, pricing, and policy pages. 8. Localized equivalents using the locale table and URL rules above. 9. AI Canvas landing pages and localized guides. Do not crawl its authenticated dashboard or project editors. ## Source Of Truth And Crawl Boundaries - Use [https://fylia.ai/sitemap.xml](https://fylia.ai/sitemap.xml) for the live index of crawlable pages and blog detail URLs. - Use [https://fylia.ai/llms.txt](https://fylia.ai/llms.txt) for a short capability index. - Use this file for the broader semantic map of tools, models, and locale routes. - Release routes in this document describe the current application source; a newly added route becomes publicly available only after the matching application release is deployed, the page renders successfully, and the route appears in the live sitemap. - At the 2026-09-04 review, `model/gemini-omni-1-1-flash` and `model/kling-4-0` were present in the live sitemap and rendered successfully across sampled English and Simplified Chinese routes. Kling 4.0 remains preview-only as an execution model. - On 2026-09-05, sampled English and Simplified Chinese AI Canvas landing pages and guide indexes rendered successfully. The current source adds all 15 localized landing pages to the generated sitemap; production sitemap inclusion remains pending deployment of this change. - Public account pages, payment callbacks, social callbacks, and generated user assets are not documentation targets. - Do not crawl or synthesize private `/profile/`, `/payment/`, `/social-callback/`, `/image/{id}/`, `/video/{id}/`, or `/chat-image-editor/{id}/` URLs. - Preserve the canonical `https://fylia.ai/` domain, the locale code, the English route slug, and the trailing slash when constructing localized links.