[{"_1":2,"_1123":-5,"_1124":-5},"loaderData",{"_3":4},"routes/docs",{"_5":6,"_7":8,"_9":10,"_11":12,"_1121":1122},"path","nodes/video/luma-ray-2.mdx","pageUrl","/docs/nodes/video/luma-ray-2","markdownUrl","/docs/nodes/video/luma-ray-2.md","pageTree",{"_13":14,"_15":16},"$fumadocs_loader","page-tree","data",{"_17":18,"_19":20,"_21":18,"_22":23,"_24":-7,"_25":26,"_1081":1082},"type","root","$ref","meta.json","$id","name","Docs","description","children",[27,163,839,907,998,1040],{"_17":28,"_22":29,"_18":30,"_31":-7,"_24":32,"_33":-7,"_25":34,"_21":161,"_19":162,"_40":95},"folder","Interface",true,"defaultOpen","Get started with Fuser","collapsible",[35,44,50,56,59,65,71,77,83,89,91,97,103,109,115,121,127,129,135,141,147,153,155],{"_21":36,"_17":37,"_22":38,"_24":39,"_40":41,"_42":43,"_19":36},"interface/index.mdx","page","Overview","Welcome to Fuser — start here.","icon","","url","/docs/interface",{"_21":45,"_17":37,"_22":46,"_24":47,"_40":48,"_42":49,"_19":45},"interface/quick-start.mdx","Quick Start","Get up and running with Fuser in minutes.","","/docs/interface/quick-start",{"_21":51,"_17":37,"_22":52,"_24":53,"_40":54,"_42":55,"_19":51},"interface/concepts.mdx","Core Concepts","The fundamental ideas behind Fuser.","","/docs/interface/concepts",{"_21":57,"_17":58,"_40":-7,"_22":-7},"_0","separator",{"_21":60,"_17":37,"_22":61,"_24":62,"_40":63,"_42":64,"_19":60},"interface/canvas.mdx","Canvas & Navigation","Move around and work on the Fuser canvas.","","/docs/interface/canvas",{"_21":66,"_17":37,"_22":67,"_24":68,"_40":69,"_42":70,"_19":66},"interface/nodes.mdx","Understanding Nodes","How nodes power Fuser flows.","","/docs/interface/nodes",{"_21":72,"_17":37,"_22":73,"_24":74,"_40":75,"_42":76,"_19":72},"interface/node-presets.mdx","Node Presets","Save a node's inputs as a reusable snapshot, then apply it to any compatible node — same type or different.","","/docs/interface/node-presets",{"_21":78,"_17":37,"_22":79,"_24":80,"_40":81,"_42":82,"_19":78},"interface/sockets.mdx","Sockets & Connections","Connect data between nodes via sockets.","","/docs/interface/sockets",{"_21":84,"_17":37,"_22":85,"_24":86,"_40":87,"_42":88,"_19":84},"interface/flows.mdx","Building Flows","Compose nodes into complete flows.","","/docs/interface/flows",{"_21":90,"_17":58,"_40":-7,"_22":-7},"_1",{"_21":92,"_17":37,"_22":93,"_24":94,"_40":95,"_42":96,"_19":92},"interface/interface.mdx","Interface Guide","A tour of the Fuser interface.","","/docs/interface/interface",{"_21":98,"_17":37,"_22":99,"_24":100,"_40":101,"_42":102,"_19":98},"interface/importing-data.mdx","Working with Media","Bring images, video, audio, and meshes into your flows.","","/docs/interface/importing-data",{"_21":104,"_17":37,"_22":105,"_24":106,"_40":107,"_42":108,"_19":104},"interface/providers.mdx","AI Providers","Connect Fuser to OpenAI, Anthropic, Google, Fal, OpenRouter, and more.","","/docs/interface/providers",{"_21":110,"_17":37,"_22":111,"_24":112,"_40":113,"_42":114,"_19":110},"interface/api-keys.mdx","Setting up API Keys","Connect your provider accounts to Fuser.","","/docs/interface/api-keys",{"_21":116,"_17":37,"_22":117,"_24":118,"_40":119,"_42":120,"_19":116},"interface/billing.mdx","Billing & Plans","Manage your personal subscription, credits, payment methods, auto-recharge, and invoices.","","/docs/interface/billing",{"_21":122,"_17":37,"_22":123,"_24":124,"_40":125,"_42":126,"_19":122},"interface/settings.mdx","Settings","Personal settings — profile, editor preferences, and email notifications.","","/docs/interface/settings",{"_21":128,"_17":58,"_40":-7,"_22":-7},"_2",{"_21":130,"_17":37,"_22":131,"_24":132,"_40":133,"_42":134,"_19":130},"interface/templates.mdx","Templates","Reusable starting points for common workflows.","","/docs/interface/templates",{"_21":136,"_17":37,"_22":137,"_24":138,"_40":139,"_42":140,"_19":136},"interface/styles.mdx","Style Training","Train custom styles on your own references.","","/docs/interface/styles",{"_21":142,"_17":37,"_22":143,"_24":144,"_40":145,"_42":146,"_19":142},"interface/sharing.mdx","Sharing & Collaboration","Share flows and collaborate with your team.","","/docs/interface/sharing",{"_21":148,"_17":37,"_22":149,"_24":150,"_40":151,"_42":152,"_19":148},"interface/focus-mode.mdx","Focus mode","A fullscreen view of a single node — your media at full size with the prompt right there.","","/docs/interface/focus-mode",{"_21":154,"_17":58,"_40":-7,"_22":-7},"_3",{"_21":156,"_17":37,"_22":157,"_24":158,"_40":159,"_42":160,"_19":156},"interface/troubleshooting.mdx","Troubleshooting","Common issues and how to resolve them.","","/docs/interface/troubleshooting","interface","interface/meta.json",{"_17":28,"_22":164,"_18":30,"_31":-7,"_24":165,"_33":-7,"_25":166,"_21":837,"_19":838,"_40":171},"Nodes","Explore every node",[167,173,244,255,314,535,736,772],{"_21":168,"_17":37,"_22":169,"_24":170,"_40":171,"_42":172,"_19":168},"nodes/index.mdx","Node Reference","Browse generated documentation for Fuser nodes, inputs, and outputs.","","/docs/nodes",{"_17":28,"_22":174,"_18":-7,"_31":30,"_24":-7,"_33":-7,"_25":175,"_21":242,"_19":243,"_40":-7},"Primitive",[176,182,188,194,200,206,212,218,224,230,236],{"_21":177,"_17":37,"_22":178,"_24":179,"_40":180,"_42":181,"_19":177},"nodes/primitive/audio.mdx","Audio","The audio node is a primitive node used to store and view audio content.","","/docs/nodes/primitive/audio",{"_21":183,"_17":37,"_22":184,"_24":185,"_40":186,"_42":187,"_19":183},"nodes/primitive/compositor.mdx","Compositor","Combine multiple media layers (images, videos, 3D) into a single composited output. Click Edit to open the full compositor editor.","","/docs/nodes/primitive/compositor",{"_21":189,"_17":37,"_22":190,"_24":191,"_40":192,"_42":193,"_19":189},"nodes/primitive/image.mdx","Image","The image node is a primitive node used to store and view image content.","","/docs/nodes/primitive/image",{"_21":195,"_17":37,"_22":196,"_24":197,"_40":198,"_42":199,"_19":195},"nodes/primitive/mesh.mdx","Mesh","The mesh node is a primitive node used to store and view 3D content.","","/docs/nodes/primitive/mesh",{"_21":201,"_17":37,"_22":202,"_24":203,"_40":204,"_42":205,"_19":201},"nodes/primitive/prompt-template.mdx","Prompt Template","A text template node with dynamic variables and inline enum selectors.","","/docs/nodes/primitive/prompt-template",{"_21":207,"_17":37,"_22":208,"_24":209,"_40":210,"_42":211,"_19":207},"nodes/primitive/style.mdx","Style","The style node stores style content.","","/docs/nodes/primitive/style",{"_21":213,"_17":37,"_22":214,"_24":215,"_40":216,"_42":217,"_19":213},"nodes/primitive/text.mdx","Text","The text node is a primitive node used to store text content.","","/docs/nodes/primitive/text",{"_21":219,"_17":37,"_22":220,"_24":221,"_40":222,"_42":223,"_19":219},"nodes/primitive/text-concat.mdx","Text Concat","Concatenates multiple text inputs into a single output.","","/docs/nodes/primitive/text-concat",{"_21":225,"_17":37,"_22":226,"_24":227,"_40":228,"_42":229,"_19":225},"nodes/primitive/text-split.mdx","Text Split","Splits text into multiple outputs by a delimiter.","","/docs/nodes/primitive/text-split",{"_21":231,"_17":37,"_22":232,"_24":233,"_40":234,"_42":235,"_19":231},"nodes/primitive/tool.mdx","Tool","Prompt-authored utility node for manual Tool testing.","","/docs/nodes/primitive/tool",{"_21":237,"_17":37,"_22":238,"_24":239,"_40":240,"_42":241,"_19":237},"nodes/primitive/video.mdx","Video","The video node is a primitive node used to store and view video content.","","/docs/nodes/primitive/video","nodes/primitive","nodes/primitive/meta.json",{"_17":28,"_22":245,"_18":-7,"_31":30,"_24":-7,"_33":-7,"_25":246,"_21":253,"_19":254,"_40":-7},"Code",[247],{"_21":248,"_17":37,"_22":249,"_24":250,"_40":251,"_42":252,"_19":248},"nodes/code/creative-code.mdx","Creative Code","Generate and run creative code with a creative coding library. Supports dynamic parameters via @fuser-params.","","/docs/nodes/code/creative-code","nodes/code","nodes/code/meta.json",{"_17":28,"_22":256,"_18":-7,"_31":30,"_24":-7,"_33":-7,"_25":257,"_21":312,"_19":313,"_40":-7},"LLM",[258,264,270,276,282,288,294,300,306],{"_21":259,"_17":37,"_22":260,"_24":261,"_40":262,"_42":263,"_19":259},"nodes/llm/chatgpt.mdx","ChatGPT","Chat with OpenAI models including GPT-5, GPT-4, and other advanced models. Supports system prompts, attachments, and fine-tuned parameter control.","","/docs/nodes/llm/chatgpt",{"_21":265,"_17":37,"_22":266,"_24":267,"_40":268,"_42":269,"_19":265},"nodes/llm/claude-chat.mdx","Claude Chat","Leverage Claude's exceptional reasoning and analysis capabilities for complex tasks. Supports system prompts, attachments, and precise parameter tuning. Excels at long-form content, analysis, and coding tasks.","","/docs/nodes/llm/claude-chat",{"_21":271,"_17":37,"_22":272,"_24":273,"_40":274,"_42":275,"_19":271},"nodes/llm/cohere-chat.mdx","Cohere Chat","Chat with Cohere models. Cohere provides powerful language models for various tasks.","","/docs/nodes/llm/cohere-chat",{"_21":277,"_17":37,"_22":278,"_24":279,"_40":280,"_42":281,"_19":277},"nodes/llm/deepseek-chat.mdx","DeepSeek Chat","Chat with DeepSeek models. DeepSeek provides powerful language models with strong reasoning capabilities.","","/docs/nodes/llm/deepseek-chat",{"_21":283,"_17":37,"_22":284,"_24":285,"_40":286,"_42":287,"_19":283},"nodes/llm/google-gemini-chat.mdx","Google Gemini Chat","Chat with Google Gemini models. Gemini provides advanced multimodal capabilities including text, image, and video understanding.","","/docs/nodes/llm/google-gemini-chat",{"_21":289,"_17":37,"_22":290,"_24":291,"_40":292,"_42":293,"_19":289},"nodes/llm/groq-chat.mdx","Groq Chat","Chat with Groq models. Groq provides fast inference for various language models.","","/docs/nodes/llm/groq-chat",{"_21":295,"_17":37,"_22":296,"_24":297,"_40":298,"_42":299,"_19":295},"nodes/llm/mistral-chat.mdx","Mistral Chat","Chat with Mistral AI models. Mistral provides efficient and powerful language models.","","/docs/nodes/llm/mistral-chat",{"_21":301,"_17":37,"_22":302,"_24":303,"_40":304,"_42":305,"_19":301},"nodes/llm/openrouter-chat.mdx","OpenRouter Chat","Chat with models from OpenRouter. Access a wide variety of language models from different providers through a single interface.","","/docs/nodes/llm/openrouter-chat",{"_21":307,"_17":37,"_22":308,"_24":309,"_40":310,"_42":311,"_19":307},"nodes/llm/perplexity-chat.mdx","Perplexity Chat","Chat with Perplexity models. Perplexity provides AI models optimized for search and reasoning tasks.","","/docs/nodes/llm/perplexity-chat","nodes/llm","nodes/llm/meta.json",{"_17":28,"_22":190,"_18":-7,"_31":30,"_24":-7,"_33":-7,"_25":315,"_21":533,"_19":534,"_40":-7},[316,322,327,332,338,343,348,354,360,365,370,376,381,386,391,396,401,406,412,418,424,429,434,439,445,450,455,460,466,471,476,481,487,492,497,502,508,513,518,523,528],{"_21":317,"_17":37,"_22":318,"_24":319,"_40":320,"_42":321,"_19":317},"nodes/image/background-remover.mdx","Background Remover","Bria RMBG 2.0 enables seamless removal of backgrounds from images, ideal for professional editing tasks. Trained exclusively on licensed data for safe and risk-free commercial use.","","/docs/nodes/image/background-remover",{"_21":323,"_17":37,"_22":324,"_24":325,"_40":320,"_42":326,"_19":323},"nodes/image/background-replacer.mdx","Background Replacer","Bria Background Replace allows for efficient swapping of backgrounds in images via text prompts or reference image, delivering realistic and polished results. Trained exclusively on licensed data for safe and risk-free commercial use.","/docs/nodes/image/background-replacer",{"_21":328,"_17":37,"_22":329,"_24":330,"_40":320,"_42":331,"_19":328},"nodes/image/bria-product-shot.mdx","Bria Product Shot","Place any product in any scenery with just a prompt or reference image while maintaining high integrity of the product. Trained exclusively on licensed data for safe and risk-free commercial use and optimized for eCommerce.","/docs/nodes/image/bria-product-shot",{"_21":333,"_17":37,"_22":334,"_24":335,"_40":336,"_42":337,"_19":333},"nodes/image/canny-edge-detection.mdx","Canny Edge Detection","Apply Canny edge detection to an image.","","/docs/nodes/image/canny-edge-detection",{"_21":339,"_17":37,"_22":340,"_24":341,"_40":336,"_42":342,"_19":339},"nodes/image/depth-anything-v2.mdx","Depth Anything V2","Generate a depth map from any image using Depth Anything V2.","/docs/nodes/image/depth-anything-v2",{"_21":344,"_17":37,"_22":345,"_24":346,"_40":336,"_42":347,"_19":344},"nodes/image/esrgan-upscaler.mdx","ESRGAN Upscaler","Upscale and enhance images using Real-ESRGAN neural networks.","/docs/nodes/image/esrgan-upscaler",{"_21":349,"_17":37,"_22":350,"_24":351,"_40":352,"_42":353,"_19":349},"nodes/image/fashn-tryon.mdx","Fashn Tryon","FASHN delivers precise virtual try-on capabilities, accurately rendering garment details like text and patterns at 576x864 resolution from both on-model and flat-lay photo references.","","/docs/nodes/image/fashn-tryon",{"_21":355,"_17":37,"_22":356,"_24":357,"_40":358,"_42":359,"_19":355},"nodes/image/fast-lcm-image-generator.mdx","Fast LCM Image Generator","Generate images very quickly using Latent Consistency Models (LCM). Produces results in seconds.","","/docs/nodes/image/fast-lcm-image-generator",{"_21":361,"_17":37,"_22":362,"_24":363,"_40":358,"_42":364,"_19":361},"nodes/image/fast-sdxl.mdx","Fast SDXL","Generate high-quality images from text prompts using Stable Diffusion XL.","/docs/nodes/image/fast-sdxl",{"_21":366,"_17":37,"_22":367,"_24":368,"_40":336,"_42":369,"_19":366},"nodes/image/florence-2-image-captioner.mdx","Florence-2 Image Captioner","Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks.","/docs/nodes/image/florence-2-image-captioner",{"_21":371,"_17":37,"_22":372,"_24":373,"_40":374,"_42":375,"_19":371},"nodes/image/flux-1-dev.mdx","FLUX.1 [Dev]","FLUX.1 [dev] is a 12 billion parameter flow transformer that generates high-quality images from text. It is suitable for personal and commercial use.","","/docs/nodes/image/flux-1-dev",{"_21":377,"_17":37,"_22":378,"_24":379,"_40":374,"_42":380,"_19":377},"nodes/image/flux-1-kontext.mdx","FLUX.1 Kontext","FLUX.1 Kontext handles both text and reference images as inputs, seamlessly enabling targeted, local edits and complex transformations of entire scenes.","/docs/nodes/image/flux-1-kontext",{"_21":382,"_17":37,"_22":383,"_24":384,"_40":374,"_42":385,"_19":382},"nodes/image/flux-2.mdx","FLUX.2","Customizable multi-reference editing with surgical control over transformation quality and prompt adherence. FLUX.2 combines up to 10 reference images with adjustable inference steps and guidance tuning for context-aware edits. Whether compositing multiple product shots, refining typography in existing designs, or blending style references, FLUX.2 delivers professional editing with granular cost-quality control—dial up steps for final deliverables, adjust guidance for creative vs. literal interpretations. FLUX.2 extends its configurable generation pipeline to image editing, understanding relationships between multiple input images while giving you direct control over the transformation process. Combine reference images, specify exact edits through natural language, and tune generation parameters to balance speed with output quality.","/docs/nodes/image/flux-2",{"_21":387,"_17":37,"_22":388,"_24":389,"_40":374,"_42":390,"_19":387},"nodes/image/flux1-1-pro-ultra.mdx","FLUX1.1 [Pro] Ultra","FLUX1.1 [pro] ultra is the newest version of FLUX1.1 [pro], maintaining professional-grade image quality while delivering up to 2K resolution with improved photo realism.","/docs/nodes/image/flux1-1-pro-ultra",{"_21":392,"_17":37,"_22":393,"_24":394,"_40":286,"_42":395,"_19":392},"nodes/image/gemini-image.mdx","Gemini Image","Google Gemini Image (Nano Banana) is a state-of-the-art generative AI model that excels at multi-image fusion, character consistency, and conversational image editing. It can merge multiple images into coherent scenes, maintain subject identity across edits, and perform targeted modifications through natural language instructions.","/docs/nodes/image/gemini-image",{"_21":397,"_17":37,"_22":398,"_24":399,"_40":262,"_42":400,"_19":397},"nodes/image/gpt-image.mdx","GPT Image","GPT Image provides powerful capabilities for image generation and manipulation. Generate images from scratch based on a text prompt, edit existing images or create variations with ease.","/docs/nodes/image/gpt-image",{"_21":402,"_17":37,"_22":403,"_24":404,"_40":336,"_42":405,"_19":402},"nodes/image/hed-edge-detection.mdx","HED Edge Detection","Apply Holistically-Nested Edge Detection (HED) to an image.","/docs/nodes/image/hed-edge-detection",{"_21":407,"_17":37,"_22":408,"_24":409,"_40":410,"_42":411,"_19":407},"nodes/image/ideogram-v2.mdx","Ideogram v2","Generate high-quality images, posters, and logos with Ideogram V2. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.","","/docs/nodes/image/ideogram-v2",{"_21":413,"_17":37,"_22":414,"_24":415,"_40":416,"_42":417,"_19":413},"nodes/image/krea.mdx","Krea","Krea generates high-fidelity images with strong aesthetics and controllable creative direction. Krea 2 is the default flagship text-to-image model, while FLUX.1 Krea [dev] remains available for open-weight Krea 1 workflows, image-to-image, and style LoRA generation.","","/docs/nodes/image/krea",{"_21":419,"_17":37,"_22":420,"_24":421,"_40":422,"_42":423,"_19":419},"nodes/image/luma-uni-1.mdx","Luma Uni-1","Luma Uni-1 is Luma’s agentic text-to-image model. It plans a scene from your prompt and can consult reference images and the web to produce coherent, detailed images, with an optional manga style.","","/docs/nodes/image/luma-uni-1",{"_21":425,"_17":37,"_22":426,"_24":427,"_40":336,"_42":428,"_19":425},"nodes/image/mlsd-line-detection.mdx","MLSD Line Detection","Apply Mobile Line Segment Detection (MLSD) to an image.","/docs/nodes/image/mlsd-line-detection",{"_21":430,"_17":37,"_22":431,"_24":432,"_40":336,"_42":433,"_19":430},"nodes/image/moondream.mdx","Moondream","Ask questions about image content using Moondream, a powerful visual language model.","/docs/nodes/image/moondream",{"_21":435,"_17":37,"_22":436,"_24":437,"_40":336,"_42":438,"_19":435},"nodes/image/moondream-detection.mdx","Moondream Detection","MoonDreamNext Detection is a multimodal vision-language model for gaze detection, bbox detection, point detection, and more.","/docs/nodes/image/moondream-detection",{"_21":440,"_17":37,"_22":441,"_24":442,"_40":443,"_42":444,"_19":440},"nodes/image/qwen-edit-angles.mdx","Qwen Edit Angles","Qwen Edit Angles is a specialized image editing tool that allows precise camera control including rotation around the subject, forward movement (to close-up), vertical angle adjustment, and wide-angle lens effects. It uses specialized LoRAs to maintain high quality and natural integration. Perfect for e-commerce, product photography, creative editing, and cinematic workflows.","","/docs/nodes/image/qwen-edit-angles",{"_21":446,"_17":37,"_22":447,"_24":448,"_40":443,"_42":449,"_19":446},"nodes/image/qwen-image-2.mdx","Qwen Image 2","Qwen Image 2 is a unified generation-and-editing model built for strong prompt adherence, realistic image quality, and high-fidelity Chinese and English typography. This node supports both text-to-image and image editing in one workflow: connect one to three images to use edit mode, or leave images empty for pure generation. You can switch between Standard and Pro tiers and tune safety, prompt expansion, size, and output format.","/docs/nodes/image/qwen-image-2",{"_21":451,"_17":37,"_22":452,"_24":453,"_40":443,"_42":454,"_19":451},"nodes/image/qwen-image.mdx","Qwen-Image","Qwen-Image is an image foundation model that achieves significant advances in complex text rendering and precise image editing. One of its standout capabilities is high-fidelity text rendering across diverse images. Whether it's alphabetic languages like English or logographic scripts like Chinese, Qwen-Image preserves typographic details, layout coherence, and contextual harmony with stunning accuracy. Text isn't just overlaid, it's seamlessly integrated into the visual fabric. Beyond text, Qwen-Image excels at general image generation with support for a wide range of artistic styles. From photorealistic scenes to impressionist paintings, from anime aesthetics to minimalist design, the model adapts fluidly to creative prompts, making it a versatile tool for artists, designers, and storytellers.","/docs/nodes/image/qwen-image",{"_21":456,"_17":37,"_22":457,"_24":458,"_40":443,"_42":459,"_19":456},"nodes/image/qwen-image-edit.mdx","Qwen-Image Edit","Qwen-Image Edit is a specialized image editing tool with multiple operations including: removing white backgrounds and adding realistic scenes, generating full portraits from face crops, creating retro-style group photos, seamlessly integrating products into backgrounds, generating cinematic scene transitions, removing unwanted elements, normalizing lighting, and applying designs to shirts. Each operation uses specialized LoRAs to maintain high quality and natural integration. Perfect for e-commerce, product photography, creative editing, and cinematic workflows.","/docs/nodes/image/qwen-image-edit",{"_21":461,"_17":37,"_22":462,"_24":463,"_40":464,"_42":465,"_19":461},"nodes/image/recraft-upscale.mdx","Recraft Upscale","Enhances a given raster image using the \"clarity upscale\" tool, increasing image resolution, making the image sharper and cleaner.","","/docs/nodes/image/recraft-upscale",{"_21":467,"_17":37,"_22":468,"_24":469,"_40":464,"_42":470,"_19":467},"nodes/image/recraft-v3.mdx","Recraft v3","Recraft is an image generation model with the ability to generate long texts, vector art, images in multiple styles, and much more. Recraft V3 is designed with professional designers in mind, providing advanced features and controls for creating high-quality graphic designs. It excels in anatomical accuracy, prompt understanding, and high aesthetic quality. The model allows for creating images that maintain consistent brand style and provides ultimate control and precision for iterations.","/docs/nodes/image/recraft-v3",{"_21":472,"_17":37,"_22":473,"_24":474,"_40":464,"_42":475,"_19":472},"nodes/image/recraft-v4.mdx","Recraft V4","Recraft V4 generates production-ready imagery for brand systems and design workflows from text prompts. Version 4.1 is the default for sharper composition, lighting, and material realism, while V4 remains available for older workflows. Use normal mode for efficient generation, pro mode for higher-end results, and switch between raster image or editable SVG-style vector output.","/docs/nodes/image/recraft-v4",{"_21":477,"_17":37,"_22":478,"_24":479,"_40":336,"_42":480,"_19":477},"nodes/image/rembg.mdx","Rembg","Remove the background from an image.","/docs/nodes/image/rembg",{"_21":482,"_17":37,"_22":483,"_24":484,"_40":485,"_42":486,"_19":482},"nodes/image/reve.mdx","Reve","Generate and edit images using Reve, a powerful image generation and editing model.","","/docs/nodes/image/reve",{"_21":488,"_17":37,"_22":489,"_24":490,"_40":336,"_42":491,"_19":488},"nodes/image/scribble-detection.mdx","Scribble Detection","Convert an image into a scribble sketch.","/docs/nodes/image/scribble-detection",{"_21":493,"_17":37,"_22":494,"_24":495,"_40":358,"_42":496,"_19":493},"nodes/image/sdxl-canny-controlnet.mdx","SDXL Canny Controlnet","Generate images with SDXL guided by Canny edge detection.","/docs/nodes/image/sdxl-canny-controlnet",{"_21":498,"_17":37,"_22":499,"_24":500,"_40":358,"_42":501,"_19":498},"nodes/image/sdxl-inpainting.mdx","SDXL Inpainting","Inpaint selected areas of an image with SDXL.","/docs/nodes/image/sdxl-inpainting",{"_21":503,"_17":37,"_22":504,"_24":505,"_40":506,"_42":507,"_19":503},"nodes/image/seedream.mdx","Seedream","Seedream 5.0 Lite delivers fast, intelligent and high quality image generation and editing suitable for creative advertising and real-world usecases. It can process up to 10 reference images simultaneously for complex multi-source compositions, with high-resolution output up to 3K (3072x3072).","","/docs/nodes/image/seedream",{"_21":509,"_17":37,"_22":510,"_24":511,"_40":443,"_42":512,"_19":509},"nodes/image/skin-enhancer.mdx","Skin Enhancer","Skin Enhancer transforms AI-generated portraits with artificial-looking skin into natural, photorealistic images. Using advanced texture processing, it removes unnatural smoothness and replaces it with realistic skin details, pores, and natural variations. Specialized for portrait enhancement based on a custom variant of Z-Image, delivering results in seconds.","/docs/nodes/image/skin-enhancer",{"_21":514,"_17":37,"_22":515,"_24":516,"_40":443,"_42":517,"_19":514},"nodes/image/wan-2-6-image.mdx","Wan 2.6 Image","Wan 2.6 is an advanced AI image generation model that excels at creating high-quality images from text prompts or transforming existing images. It delivers exceptional detail, artistic coherence, and prompt adherence, making it ideal for creative workflows requiring both text-to-image and image-to-image capabilities.","/docs/nodes/image/wan-2-6-image",{"_21":519,"_17":37,"_22":520,"_24":521,"_40":443,"_42":522,"_19":519},"nodes/image/wan-2-2-image.mdx","Wan-2.2 Image","Wan-2.2 generates high-resolution, photorealistic images with powerful prompt understanding and fine-grained visual detail. It achieves professional cinematic quality, offering fine-grained control over lighting, color, and composition for versatile styles with delicate detail. Wan-2.2 can generalize across multiple dimensions such as semantics, structure, and aesthetics, with better understanding and execution of prompts for complex scenes and multi-object generation.","/docs/nodes/image/wan-2-2-image",{"_21":524,"_17":37,"_22":525,"_24":526,"_40":443,"_42":527,"_19":524},"nodes/image/z-image.mdx","Z-Image","Z-Image is a fast and efficient image generation model from Alibaba. It delivers photorealistic images with excellent aesthetic quality and excels at accurately rendering both Chinese and English text directly in generated images. With built-in prompt enhancement and reasoning capabilities, Z-Image helps bring your creative visions to life with sub-second inference speed.","/docs/nodes/image/z-image",{"_21":529,"_17":37,"_22":530,"_24":531,"_40":336,"_42":532,"_19":529},"nodes/image/zoe-depth-map.mdx","Zoe Depth Map","Generate a depth map from any image using the Zoe model.","/docs/nodes/image/zoe-depth-map","nodes/image","nodes/image/meta.json",{"_17":28,"_22":238,"_18":-7,"_31":30,"_24":-7,"_33":-7,"_25":536,"_21":734,"_19":735,"_40":-7},[537,542,548,553,558,564,569,575,580,585,591,596,601,606,611,617,622,628,633,638,643,649,655,661,666,671,676,681,686,692,698,703,708,714,719,724,729],{"_21":538,"_17":37,"_22":539,"_24":540,"_40":358,"_42":541,"_19":538},"nodes/video/animatediff.mdx","AnimateDiff","AnimateDiff allows you to transform text and video prompts into dynamic videos with a wide range of motion types.","/docs/nodes/video/animatediff",{"_21":543,"_17":37,"_22":544,"_24":545,"_40":546,"_42":547,"_19":543},"nodes/video/auto-caption.mdx","Auto Caption","Automatically generates text captions for your videos from the audio as per text colour/font specifications.","","/docs/nodes/video/auto-caption",{"_21":549,"_17":37,"_22":550,"_24":551,"_40":358,"_42":552,"_19":549},"nodes/video/fast-svd-video-generator.mdx","Fast SVD Video Generator","Generate high-quality videos from text prompts using the SVD model. Creates short animations quickly.","/docs/nodes/video/fast-svd-video-generator",{"_21":554,"_17":37,"_22":555,"_24":556,"_40":286,"_42":557,"_19":554},"nodes/video/gemini-omni-video.mdx","Gemini Omni Video","Gemini Omni Flash is a public-preview Google video model for 720p text-to-video, image-guided video, and video-to-video generation.","/docs/nodes/video/gemini-omni-video",{"_21":559,"_17":37,"_22":560,"_24":561,"_40":562,"_42":563,"_19":559},"nodes/video/grok-imagine.mdx","Grok Imagine","Grok Imagine Video generates video with synchronized audio from text prompts, single images, or multiple reference images using xAI's Grok model. In text-to-video mode, describe your scene to produce realistic footage up to 15 seconds. Provide a single image to animate it as the first frame. Supply two to seven reference images and cite them in your prompt as @Image1 through @Image7 to blend their visual features into a single coherent video. Outputs up to 720p resolution.","","/docs/nodes/video/grok-imagine",{"_21":565,"_17":37,"_22":566,"_24":567,"_40":562,"_42":568,"_19":565},"nodes/video/grok-imagine-edit.mdx","Grok Imagine Edit","Grok Imagine Video Edit & Extend applies xAI's Grok model to transform or continue existing video footage. In Edit mode, supply a video and a text description of the desired change — such as colorizing, restyling, or modifying scene elements — and receive an edited version at up to 720p resolution. In Extend mode, provide a video up to 15 seconds long and a prompt describing what should happen next to seamlessly append 2–10 seconds of new footage to the end of your clip.","/docs/nodes/video/grok-imagine-edit",{"_21":570,"_17":37,"_22":571,"_24":572,"_40":573,"_42":574,"_19":570},"nodes/video/hailuo-02.mdx","Hailuo 02","Hailuo 02, developed by MiniMax, is a cinematic AI video generation model that has gained attention for its high-quality output. Hailuo 02 accurately simulates object interactions, fluid dynamics, and natural motion patterns, including handling extreme physics such as acrobatics. It produces professional-grade visual fidelity with perfect lighting and composition, suitable for film, marketing, education, and social media content creation. Hailuo 02 features facial recognition and body tracking, maintaining consistent character appearances across frames, addressing a common AI video challenge.","","/docs/nodes/video/hailuo-02",{"_21":576,"_17":37,"_22":577,"_24":578,"_40":573,"_42":579,"_19":576},"nodes/video/hailuo-2-3.mdx","Hailuo 2.3","MiniMax Hailuo 2.3 builds upon the Hailuo 02 model, to further enhance dynamic expression, resulting in more realistic and stable visuals. The Hailuo 2.3 model achieves significant improvements in the portrayal of physical actions, stylization, and character micro-expressions, while further optimizing its response to motion commands. With enhanced understanding of physics and command following, Hailuo 2.3 can render more complex character body movements with greater fluidity, naturalness, precision, and control. Even with dynamic camera movements, it achieves near-photorealistic visual effects in lighting direction, shadow transitions, and color tones. Hailuo 2.3 offers better support for anime, illustration, as well as special art styles like ink wash painting and game CG.","/docs/nodes/video/hailuo-2-3",{"_21":581,"_17":37,"_22":582,"_24":583,"_40":336,"_42":584,"_19":581},"nodes/video/heygen.mdx","HeyGen","HeyGen Avatar 4 turns a single portrait image into a talking avatar video. Drive the performance with an audio track, or write a prompt and choose a voice for HeyGen to generate the speech. Control aspect ratio, resolution, captions, and talking style for the final video.","/docs/nodes/video/heygen",{"_21":586,"_17":37,"_22":587,"_24":588,"_40":589,"_42":590,"_19":586},"nodes/video/kling-1-6-video.mdx","Kling 1.6 Video","Generate video clips from your prompts using Kling 1.6 (pro).","","/docs/nodes/video/kling-1-6-video",{"_21":592,"_17":37,"_22":593,"_24":594,"_40":589,"_42":595,"_19":592},"nodes/video/kling-2-x-video-tool.mdx","Kling 2.X Video Tool","Kling excels at creating cinema-grade videos with advanced 3D spatiotemporal attention technology. Key strengths include exceptional image-to-video conversion, realistic motion physics, fast generation speeds, and strong prompt adherence. Kling particularly shines in complex motion sequences, emotional expressions, and dynamic action scenes. Although it struggles with text generation consistency and multi-subject scenes, it is ideal for creators prioritizing image animation and cinematic realism. Kling is developed by Kuaishou and is currently available in 4 variants: 2.6 Pro, 2.5 Turbo Pro, 2.1 Standard, 2.1 Pro, and 2.1 Master.","/docs/nodes/video/kling-2-x-video-tool",{"_21":597,"_17":37,"_22":598,"_24":599,"_40":589,"_42":600,"_19":597},"nodes/video/kling-3-0-motion.mdx","Kling 3.0 Motion","Transfer movements from a reference video to any character image using Kling 3.0 motion control. Provide a reference image for character appearance and a reference video for motion patterns — the model animates the character following the video's movements. Supports two orientation modes: Video for complex full-body motions (up to 30s) and Image for camera-following animations (up to 10s).","/docs/nodes/video/kling-3-0-motion",{"_21":602,"_17":37,"_22":603,"_24":604,"_40":589,"_42":605,"_19":602},"nodes/video/kling-3-0-video.mdx","Kling 3.0 Video","Kling 3.0 Standard: Top-tier text-to-video with cinematic visuals, fluid motion, and native audio generation, with multi-shot support.","/docs/nodes/video/kling-3-0-video",{"_21":607,"_17":37,"_22":608,"_24":609,"_40":336,"_42":610,"_19":607},"nodes/video/latentsync.mdx","LatentSync","LatentSync is a video-to-video model that generates lip sync animations from audio using advanced algorithms for high-quality synchronization.","/docs/nodes/video/latentsync",{"_21":612,"_17":37,"_22":613,"_24":614,"_40":615,"_42":616,"_19":612},"nodes/video/ltx.mdx","LTX","LTX-Video is a video generation model that can generate high-quality videos in real-time, faster than it takes to watch them. Trained on a dataset of diverse videos, LTX can generate high-resolution videos with realistic and diverse content.","","/docs/nodes/video/ltx",{"_21":618,"_17":37,"_22":619,"_24":620,"_40":615,"_42":621,"_19":618},"nodes/video/ltx-2-0.mdx","LTX 2.0","LTX-2 is a next-generation open-source video model that generates synchronized audio and video together in one coherent process. It supports up to 4K resolution at 50 fps with motion, dialogue, ambience, and music flowing simultaneously. Choose Fast mode for quick previews and high-throughput ideation, or Pro mode for balanced performance with strong fidelity. With support for image-to-video, text-to-video, and video retakes, LTX-2 offers creative flexibility at a fraction of the compute cost.","/docs/nodes/video/ltx-2-0",{"_21":623,"_17":37,"_22":624,"_24":625,"_40":626,"_42":627,"_19":623},"nodes/video/lucy.mdx","Lucy","Lucy, developed by Decart, is a near-realtime video generation model capable of generating high-quality output. Based on an accelerated Wan-2.2 architecture, an leveraging Decart's inference stack, Lucy can produce professional-grade visual fidelity in the blink of an eye.","","/docs/nodes/video/lucy",{"_21":629,"_17":37,"_22":630,"_24":631,"_40":422,"_42":632,"_19":629},"nodes/video/luma-ray.mdx","Luma Ray","Luma Ray generates cinematic video from prompts, images, or source footage, with model selection for Ray 3.2, Ray 2, and Ray 2 Flash. Ray 3.2 is the default and includes generate, reframe, and video edit modes, while Ray 2 and Flash remain available for older workflows and faster generation.","/docs/nodes/video/luma-ray",{"_21":634,"_17":37,"_22":635,"_24":636,"_40":422,"_42":637,"_19":634},"nodes/video/luma-video.mdx","Luma Video","Luma Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability.","/docs/nodes/video/luma-video",{"_21":639,"_17":37,"_22":640,"_24":641,"_40":336,"_42":642,"_19":639},"nodes/video/mirelo-sfx.mdx","Mirelo SFX","Mirelo SFX 1.6 generates synchronized sound effects for a video. Provide a clip and an optional text prompt, and the model adds a matching sound-effects track, returning the video with audio.","/docs/nodes/video/mirelo-sfx",{"_21":644,"_17":37,"_22":645,"_24":646,"_40":647,"_42":648,"_19":644},"nodes/video/pika.mdx","Pika","Pika is an video generation model with high visual quality, motion diversity, text-video alignment, and generation stability.","","/docs/nodes/video/pika",{"_21":650,"_17":37,"_22":651,"_24":652,"_40":653,"_42":654,"_19":650},"nodes/video/reactor-longlive-2.mdx","Reactor LongLive 2","LongLive 2 is a Reactor real-time video model for continuous multi-shot generation. Start a live session from a text prompt, steer it with soft shot changes or hard scene cuts, then stop and save the streamed recording as a video output.","","/docs/nodes/video/reactor-longlive-2",{"_21":656,"_17":37,"_22":657,"_24":658,"_40":659,"_42":660,"_19":656},"nodes/video/runway-act-two.mdx","Runway Act-Two","Act-Two allows you to animate characters using driving performance videos. By providing a driving performance of someone acting out a scene and a character reference (image or video), Act-Two transfers the movement to your character, bringing them to life with realistic motion, speech, and expression.","","/docs/nodes/video/runway-act-two",{"_21":662,"_17":37,"_22":663,"_24":664,"_40":659,"_42":665,"_19":662},"nodes/video/runway-aleph.mdx","Runway Aleph","Runway Aleph is a state-of-the-art in-context video model, setting a new frontier for multi-task visual generation, with the ability to perform a wide range of edits on an input video such as adding, removing, and transforming objects, generating any angle of a scene, and modifying style and lighting, among many other tasks.","/docs/nodes/video/runway-aleph",{"_21":667,"_17":37,"_22":668,"_24":669,"_40":659,"_42":670,"_19":667},"nodes/video/runway-video.mdx","Runway Video","With Runway Gen-3 and Gen-4 video models, you can generate consistent characters, locations and objects across scenes. Set your look and feel and the model will maintain coherent world environments while preserving the distinctive style, mood and cinematographic elements of each frame.","/docs/nodes/video/runway-video",{"_21":672,"_17":37,"_22":673,"_24":674,"_40":506,"_42":675,"_19":672},"nodes/video/seedance.mdx","Seedance","Seedance is a large-scale video generative model that supports multi-shot video generation from both text and image. It achieves breakthroughs in semantic understanding and prompt following, and can create videos with smooth motion, rich details, and cinematic aesthetics. It features a wide dynamic range, enabling smooth generation of large-scale movements. From subtle expressions to active scenes, it maintains a high level of stability and physical realism. Seedance can accurately interpret diverse stylistic prompts to support a wide range of creative needs, from photorealism and cyberpunk to illustration and felt texture.","/docs/nodes/video/seedance",{"_21":677,"_17":37,"_22":678,"_24":679,"_40":506,"_42":680,"_19":677},"nodes/video/seedance-2.mdx","Seedance 2","Seedance 2.0 is ByteDance\\u2019s most advanced video generation model, producing cinematic output with native synchronized audio, real-world physics, and director-level camera control. It supports text-to-video, image-to-video, and reference-to-video generation with durations up to 15 seconds, and offers a Fast mode for quicker results at reduced cost.","/docs/nodes/video/seedance-2",{"_21":682,"_17":37,"_22":683,"_24":684,"_40":506,"_42":685,"_19":682},"nodes/video/seedvr-upscale.mdx","SeedVR Upscale","Professional-grade video upscaling powered by SeedVR2 technology. Transform your videos with stunning clarity and detail while maintaining smooth, consistent motion throughout every frame. This advanced upscaling model delivers exceptional results faster than traditional methods, preserving the natural look and feel of your content. Perfect for enhancing footage from any source—whether you're working with lower-resolution recordings, restoring archived videos, or preparing content for high-definition display. SeedVR2 intelligently adapts to different video resolutions and frame rates, ensuring your upscaled videos look polished and professional with vibrant colors, sharp details, and seamless motion that stays true to the original.","/docs/nodes/video/seedvr-upscale",{"_21":687,"_17":37,"_22":688,"_24":689,"_40":690,"_42":691,"_19":687},"nodes/video/sora-2.mdx","Sora 2","Sora 2 is OpenAI's powerful media generation model, generating videos with synced audio. It generates videos that are physically accurate, realistic, and more controllable than prior systems. It also features synchronized dialogue and sound effects. It can create richly detailed, dynamic clips from natural language or images. Sora 2 can do things that are exceptionally difficult—and in some instances outright impossible—for prior video generation models. Sora 2is also a big leap forward in controllability, able to follow intricate instructions spanning multiple shots while accurately persisting world state. It excels at realistic, cinematic, and anime styles.","","/docs/nodes/video/sora-2",{"_21":693,"_17":37,"_22":694,"_24":695,"_40":696,"_42":697,"_19":693},"nodes/video/topaz-upscale.mdx","Topaz Upscale","Professional-grade video upscaling using Topaz technology. Enhance your videos with high-quality upscaling.","","/docs/nodes/video/topaz-upscale",{"_21":699,"_17":37,"_22":700,"_24":701,"_40":336,"_42":702,"_19":699},"nodes/video/veed-subtitles.mdx","Veed Subtitles","Veed Subtitles burns styled, animated captions into a video. Pick a subtitle preset and the model transcribes the audio (or uses your own SRT), then renders the subtitles onto the clip and returns the finished video.","/docs/nodes/video/veed-subtitles",{"_21":704,"_17":37,"_22":705,"_24":706,"_40":286,"_42":707,"_19":704},"nodes/video/veo.mdx","Veo","Veo is designed to handle a range of video generation tasks, from cinematic narratives to dynamic character animations. With Veo 3, you can create more immersive experiences by not only generating stunning visuals, but also audio like dialogue and sound effects.","/docs/nodes/video/veo",{"_21":709,"_17":37,"_22":710,"_24":711,"_40":712,"_42":713,"_19":709},"nodes/video/vidu.mdx","Vidu","Vidu is a state-of-the-art video generation model for producing high-fidelity videos with cinematic transitions, and consistent characters from simple text or image prompts. Leveraging advanced semantic understanding, Vidu delivers smooth, coherent motion and studio-quality results, particularly excelling at anime and manga video generation. The Q2 variant emphasizes subtle facial expressions, believable micro-acting (blinks, eye movements, lip sync), and smooth camera grammar with stable push-ins, pull-backs, and tracking shots. Q2 offers faster, more predictable generation with up to 8 seconds clip lengths, first-frame control, and adjustable resolution. It excels at character-driven shorts, product reveals, and stylized motion with improved expression fidelity, camera stability, and prompt adherence compared to Q1.","","/docs/nodes/video/vidu",{"_21":715,"_17":37,"_22":716,"_24":717,"_40":712,"_42":718,"_19":715},"nodes/video/vidu-reference.mdx","Vidu Reference","Vidu Reference is a video generation model that enables seamless interaction between multiple subjects, including characters, props, objects, and environments in the same scene. This model is ideal for creating videos with complex scenes and multiple characters, where characters interact naturally within the same scene. Vidu supports feature fusion, allowing elements from different subjects—such as the front of Character A and the back of Character B—to merge seamlessly into a new character or object.","/docs/nodes/video/vidu-reference",{"_21":720,"_17":37,"_22":721,"_24":722,"_40":336,"_42":723,"_19":720},"nodes/video/wan-2-1.mdx","Wan-2.1","Wan-2.1 is an advanced and powerful visual generation model developed by Tongyi Lab. It can generate videos based on text, images and other control signals. Wan-2.1 excels at generating realistic videos featuring extensive body movements, complex rotations, dynamic scene transitions, and fluid camera motions, and can accurately simulate real-world physics and realistic object interactions, while offering movie-like visuals with rich textures and a variety of stylized effects. It can also create text and dynamic text effects in videos directly from text prompts.","/docs/nodes/video/wan-2-1",{"_21":725,"_17":37,"_22":726,"_24":727,"_40":443,"_42":728,"_19":725},"nodes/video/wan-2-2-video.mdx","Wan-2.2 Video","Wan-2.2 is a leading-edge and highly capable image and video generation model developed by Tongyi Lab of Alibaba Group. Wan-2.2 achieves professional cinematic narratives through a deep command of shot language, offering fine-grained control over lighting, color, and composition for versatile styles with delicate detail. It effortlessly recreates all kinds of complex motion, with enhanced fluidity and control, with better understanding and execution of prompts for complex scenes and multi-object generation. Wan-2.2 can generalize across multiple dimensions such as motions, semantics, and aesthetics. In addition to text-to-video and image-to-video, Wan-2.2 also supports video-to-video generation, with the ability to perform a wide range of edits on an input video such as adding, removing, and transforming objects.","/docs/nodes/video/wan-2-2-video",{"_21":730,"_17":37,"_22":731,"_24":732,"_40":443,"_42":733,"_19":730},"nodes/video/wan-2-6-video.mdx","Wan-2.6 Video","Wan 2.6 is an advanced AI video generation model featuring smart shot scheduling for multi-shot storytelling, higher-quality voice generation with stable multi-speaker dialogue, and natural, realistic voices. It accurately generates multi-shot sequences to express a full story while keeping key details consistent between shots, and can auto-plan scenes from simple prompts. Wan 2.6 supports video generation up to 15 seconds, creating 1080p videos at 24fps with native audio-visual synchronization, ensuring dialogue, music, and sound effects align perfectly with character movements and lip-sync. It includes video reference generation that uses a reference video for look and voice, then follows your prompt to create new clips. Supports text-to-video, image-to-video, and video-to-video generation.","/docs/nodes/video/wan-2-6-video","nodes/video","nodes/video/meta.json",{"_17":28,"_22":178,"_18":-7,"_31":30,"_24":-7,"_33":-7,"_25":737,"_21":770,"_19":771,"_40":-7},[738,743,748,753,759,764],{"_21":739,"_17":37,"_22":740,"_24":741,"_40":336,"_42":742,"_19":739},"nodes/audio/elevenlabs-sfx.mdx","ElevenLabs SFX","Generate sound effects from a text description using ElevenLabs Sound Effects on Fal. Turn prompts into sound effects for videos, voice-overs, or games.","/docs/nodes/audio/elevenlabs-sfx",{"_21":744,"_17":37,"_22":745,"_24":746,"_40":336,"_42":747,"_19":744},"nodes/audio/elevenlabs-tts.mdx","ElevenLabs TTS","Generate natural, expressive speech from text with ElevenLabs Eleven v3 on Fal. Eleven v3 is ElevenLabs’ most emotionally rich text-to-speech model, with fine-grained control over delivery and support for many languages. Pick a voice, tune stability for more consistent or more varied performances, and optionally pin a language for reliable pronunciation.","/docs/nodes/audio/elevenlabs-tts",{"_21":749,"_17":37,"_22":750,"_24":751,"_40":336,"_42":752,"_19":749},"nodes/audio/f5-tts.mdx","F5 TTS","Text-to-speech synthesis tool that leverages AI to generate natural and expressive speech from text input.","/docs/nodes/audio/f5-tts",{"_21":754,"_17":37,"_22":755,"_24":756,"_40":757,"_42":758,"_19":754},"nodes/audio/minimax-music.mdx","Minimax Music","Generate music from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality, diverse musical compositions.","","/docs/nodes/audio/minimax-music",{"_21":760,"_17":37,"_22":761,"_24":762,"_40":336,"_42":763,"_19":760},"nodes/audio/mmaudio.mdx","MMAudio","MMAudio generates synchronized audio given video and/or text inputs. It can be combined with video models to get videos with audio.","/docs/nodes/audio/mmaudio",{"_21":765,"_17":37,"_22":766,"_24":767,"_40":768,"_42":769,"_19":765},"nodes/audio/whisper.mdx","Whisper","Transcribe and translate speech to text using OpenAI's Whisper model.","","/docs/nodes/audio/whisper","nodes/audio","nodes/audio/meta.json",{"_17":28,"_22":196,"_18":-7,"_31":30,"_24":-7,"_33":-7,"_25":773,"_21":835,"_19":836,"_40":-7},[774,780,785,790,796,801,806,811,817,823,829],{"_21":775,"_17":37,"_22":776,"_24":777,"_40":778,"_42":779,"_19":775},"nodes/mesh/hunyuan-motion.mdx","Hunyuan Motion","Hunyuan Motion generates 3D human motion animations from text descriptions. Create realistic motion capture data from natural language prompts.","","/docs/nodes/mesh/hunyuan-motion",{"_21":781,"_17":37,"_22":782,"_24":783,"_40":778,"_42":784,"_19":781},"nodes/mesh/hunyuan3d-multiview.mdx","Hunyuan3D Multiview","Hunyuan3D Multiview is a 3D model generation model that can generate realistic and production ready 3D models from images.","/docs/nodes/mesh/hunyuan3d-multiview",{"_21":786,"_17":37,"_22":787,"_24":788,"_40":778,"_42":789,"_19":786},"nodes/mesh/hunyuan3d-v3.mdx","Hunyuan3D V3","Hunyuan3D V3 generates production-ready 3D assets across three modes: text-to-3D, image-to-3D, and sketch-to-3D. It returns export-ready GLB output and lets you tune mesh density, generation style, and polygon layout to fit different quality or performance targets. Optional PBR generation helps you move from concept to renderable assets with less manual material setup.","/docs/nodes/mesh/hunyuan3d-v3",{"_21":791,"_17":37,"_22":792,"_24":793,"_40":794,"_42":795,"_19":791},"nodes/mesh/meshy.mdx","Meshy","Generate production-ready 3D meshes from reference images with Meshy. Keep Meshy 5 when you want single-image or multi-image reconstruction from up to four views, or switch to Meshy 6 for the latest single-image model with stronger geometry and texture quality. Both versions expose remeshing, topology, polycount, symmetry, and texture guidance controls.","","/docs/nodes/mesh/meshy",{"_21":797,"_17":37,"_22":798,"_24":799,"_40":794,"_42":800,"_19":797},"nodes/mesh/meshy-5-remesh.mdx","Meshy 5 Remesh","Meshy 5 Remesh rebuilds topology on existing 3D models so you can clean up geometry and target a more production-friendly polycount. Use it to convert source assets into cleaner quad or triangle meshes while preserving the original shape for downstream DCC, game, or realtime workflows. Meshy supports multi-format export, and this node returns the GLB result for consistent handoff.","/docs/nodes/mesh/meshy-5-remesh",{"_21":802,"_17":37,"_22":803,"_24":804,"_40":794,"_42":805,"_19":802},"nodes/mesh/meshy-5-retexture.mdx","Meshy 5 Retexture","Meshy 5 Retexture applies new, high-quality textures to existing 3D models using either text prompts or reference images. It supports PBR material generation for realistic, production-ready results.. Meshy Retexture provides granular control over the retexturing process, including the ability to control the topology, polycount, and symmetry of the generated model. Additional control over texture generation is also available, including the ability to provide a texture prompt and a guiding texture image. Meshy Retexture is perfect for rapid prototyping, concept visualization, game asset creation, e-commerce, and digital twins.","/docs/nodes/mesh/meshy-5-retexture",{"_21":807,"_17":37,"_22":808,"_24":809,"_40":794,"_42":810,"_19":807},"nodes/mesh/meshy-rigging.mdx","Meshy Rigging","Meshy Rigging automatically adds a skeleton to a humanoid 3D model so it is ready to pose and animate. Provide a GLB character with clearly defined limbs and Meshy returns a rigged GLB, with the option to apply an animation preset from its library. Great for turning static generated characters into animation-ready assets for games, video, and realtime workflows.","/docs/nodes/mesh/meshy-rigging",{"_21":812,"_17":37,"_22":813,"_24":814,"_40":815,"_42":816,"_19":812},"nodes/mesh/rodin.mdx","Rodin","Rodin by Hyper3D generates realistic, production-ready 3D models from text or images. Use the model selector to run Rodin 2.5 by default for improved geometry detail and texture quality, or switch back to the original Rodin endpoint for older workflows.","","/docs/nodes/mesh/rodin",{"_21":818,"_17":37,"_22":819,"_24":820,"_40":821,"_42":822,"_19":818},"nodes/mesh/sam-3d-objects.mdx","SAM 3D Objects","SAM 3D Objects reconstructs one or more objects from a single image, producing geometry and texture for downstream 3D workflows. It supports prompt-guided auto-segmentation in cluttered real-world scenes and returns production-ready GLB output. This makes it useful for product digitization, AR pipelines, and fast asset prototyping from existing photos.","","/docs/nodes/mesh/sam-3d-objects",{"_21":824,"_17":37,"_22":825,"_24":826,"_40":827,"_42":828,"_19":824},"nodes/mesh/trellis-2.mdx","Trellis 2","Trellis 2 is a native image-to-3D model that generates versatile, high-quality 3D assets from a single reference image. It reconstructs geometry and appearance into a textured GLB while exposing detailed control over resolution, remeshing, and mesh decimation. Separate structure and texture guidance settings let you balance faithful reconstruction against cleaner, more stylized output.","","/docs/nodes/mesh/trellis-2",{"_21":830,"_17":37,"_22":831,"_24":832,"_40":833,"_42":834,"_19":830},"nodes/mesh/tripo-3d.mdx","Tripo 3D","Tripo 3D v2.5 generates high-fidelity 3D models from a required front image with fast single-image reconstruction. Add left, right, or back views to switch into multiview generation when you need stronger geometric consistency. The node also exposes texture quality, quad mesh, face limit, alignment, and PBR controls so you can tune output quality and format for production workflows.","","/docs/nodes/mesh/tripo-3d","nodes/mesh","nodes/mesh/meta.json","nodes","nodes/meta.json",{"_17":28,"_22":840,"_18":30,"_31":-7,"_24":841,"_33":-7,"_25":842,"_21":904,"_19":905,"_40":906},"Teams","Workspaces, teams, and access",[843,847,853,859,864,870,876,878,884,890,892,898],{"_21":844,"_17":37,"_22":38,"_24":845,"_40":41,"_42":846,"_19":844},"teams/index.mdx","Workspaces, teams, folders, and access in Fuser.","/docs/teams",{"_21":848,"_17":37,"_22":849,"_24":850,"_40":851,"_42":852,"_19":848},"teams/workspaces.mdx","Workspaces","Create a workspace, switch between them, and edit the workspace profile.","","/docs/teams/workspaces",{"_21":854,"_17":37,"_22":855,"_24":856,"_40":857,"_42":858,"_19":854},"teams/members.mdx","Members","Invite people, assign roles, and manage your workspace's members.","","/docs/teams/members",{"_21":860,"_17":37,"_22":840,"_24":861,"_40":862,"_42":863,"_19":860},"teams/team-groups.mdx","Group members into teams with their own visibility, folders, and roles.","","/docs/teams/team-groups",{"_21":865,"_17":37,"_22":866,"_24":867,"_40":868,"_42":869,"_19":865},"teams/folders.mdx","Folders","Organize projects into folders, set default access, and choose folder visibility.","","/docs/teams/folders",{"_21":871,"_17":37,"_22":872,"_24":873,"_40":874,"_42":875,"_19":871},"teams/transferring-projects.mdx","Transferring Projects","Move a personal project into one of your workspaces, picking exactly where it lands.","","/docs/teams/transferring-projects",{"_21":877,"_17":58,"_40":-7,"_22":-7},"_4",{"_21":879,"_17":37,"_22":880,"_24":881,"_40":882,"_42":883,"_19":879},"teams/sharing.mdx","Sharing","Share projects with specific people, teams, or external collaborators.","","/docs/teams/sharing",{"_21":885,"_17":37,"_22":886,"_24":887,"_40":888,"_42":889,"_19":885},"teams/access-reference.mdx","Access Reference","The full rules of who can see what, with edge cases and scenarios.","","/docs/teams/access-reference",{"_21":891,"_17":58,"_40":-7,"_22":-7},"_5",{"_21":893,"_17":37,"_22":894,"_24":895,"_40":896,"_42":897,"_19":893},"teams/workspace-settings.mdx","Workspace Settings","Access defaults, sharing policies, verified domains, audit, recovery, and notifications.","","/docs/teams/workspace-settings",{"_21":899,"_17":37,"_22":900,"_24":901,"_40":902,"_42":903,"_19":899},"teams/workspace-billing.mdx","Workspace Billing","The workspace's plan, seats, shared credits, spend limits, and invoices.","","/docs/teams/workspace-billing","teams","teams/meta.json","",{"_17":28,"_22":908,"_18":30,"_31":-7,"_24":909,"_33":-7,"_25":910,"_21":996,"_19":997,"_40":914},"Apps","Build, preview, publish, and share live apps from a single node.",[911,916,922,924,930,936,942,948,950,956,962,964,970,976,982,988,990],{"_21":912,"_17":37,"_22":38,"_24":913,"_40":914,"_42":915,"_19":912},"apps/index.mdx","Build a live, AI-authored web app from a single node — describe it, preview it live, publish to a public URL in one click.","","/docs/apps",{"_21":917,"_17":37,"_22":918,"_24":919,"_40":920,"_42":921,"_19":917},"apps/quickstart.mdx","Quickstart","Add an App node, describe an app, watch it build, and publish it — start to finish.","","/docs/apps/quickstart",{"_21":923,"_17":58,"_40":-7,"_22":-7},"_6",{"_21":925,"_17":37,"_22":926,"_24":927,"_40":928,"_42":929,"_19":925},"apps/building.mdx","Building with the agent","The composer, generation activity, crafting prompts, fixing errors, and answering the agent's optional questions.","","/docs/apps/building",{"_21":931,"_17":37,"_22":932,"_24":933,"_40":934,"_42":935,"_19":931},"apps/models.mdx","Generation models & creativity","Pick the model that builds your app — Free, Standard, Pro, or Max — and tune how adventurous it is.","","/docs/apps/models",{"_21":937,"_17":37,"_22":938,"_24":939,"_40":940,"_42":941,"_19":937},"apps/editing.mdx","Editing your app directly","Beyond prompting — edit content, design tokens, media, and code by hand, with the agent's help where you want it.","","/docs/apps/editing",{"_21":943,"_17":37,"_22":944,"_24":945,"_40":946,"_42":947,"_19":943},"apps/preview.mdx","Preview & focus mode","The full-screen workspace, the live preview, viewport sizes, and the actions tucked into the preview toolbar.","","/docs/apps/preview",{"_21":949,"_17":58,"_40":-7,"_22":-7},"_7",{"_21":951,"_17":37,"_22":952,"_24":953,"_40":954,"_42":955,"_19":951},"apps/inputs.mdx","Connecting inputs","Feed references, media, and data into your app through the node's sockets — or attach them right from focus mode.","","/docs/apps/inputs",{"_21":957,"_17":37,"_22":958,"_24":959,"_40":960,"_42":961,"_19":957},"apps/data-and-backends.mdx","Data & backends","Give your app a real backend — a database, API, or file storage — with Resource nodes, and build realtime, multiplayer apps.","","/docs/apps/data-and-backends",{"_21":963,"_17":58,"_40":-7,"_22":-7},"_8",{"_21":965,"_17":37,"_22":966,"_24":967,"_40":968,"_42":969,"_19":965},"apps/publishing.mdx","Publishing & versions","Take an app live, move between versions, roll back, and understand the plan limits on published apps.","","/docs/apps/publishing",{"_21":971,"_17":37,"_22":972,"_24":973,"_40":974,"_42":975,"_19":971},"apps/sharing.mdx","Sharing & your audience","The public URL, QR codes, discovery listings, the \"Made with Fuser\" badge, and what visitors can and can't see.","","/docs/apps/sharing",{"_21":977,"_17":37,"_22":978,"_24":979,"_40":980,"_42":981,"_19":977},"apps/managing-apps.mdx","Managing your apps","Find, reopen, and reuse every app you've built — from the Apps panel and the My Apps grid.","","/docs/apps/managing-apps",{"_21":983,"_17":37,"_22":984,"_24":985,"_40":986,"_42":987,"_19":983},"apps/remixing.mdx","Forking & fusing","Branch an app into a new direction, or blend a feature from one app into another.","","/docs/apps/remixing",{"_21":989,"_17":58,"_40":-7,"_22":-7},"_9",{"_21":991,"_17":37,"_22":992,"_24":993,"_40":994,"_42":995,"_19":991},"apps/troubleshooting.mdx","Troubleshooting & FAQ","What to do when a build fails, an app won't open, or a message looks unfamiliar — plus answers to common questions.","","/docs/apps/troubleshooting","apps","apps/meta.json",{"_17":28,"_22":184,"_18":30,"_31":-7,"_24":999,"_33":-7,"_25":1000,"_21":1038,"_19":1039,"_40":1004},"Layer and composite media into final outputs.",[1001,1006,1011,1013,1019,1024,1030,1032],{"_21":1002,"_17":37,"_22":38,"_24":1003,"_40":1004,"_42":1005,"_19":1002},"compositor/index.mdx","Layer and composite media into final outputs inside Fuser's full-screen visual editor.","","/docs/compositor",{"_21":1007,"_17":37,"_22":1008,"_24":1009,"_40":54,"_42":1010,"_19":1007},"compositor/concepts.mdx","Concepts","How the Compositor thinks about scenes, layers, masks, the canvas, and live collaboration.","/docs/compositor/concepts",{"_21":1012,"_17":58,"_40":-7,"_22":-7},"_10",{"_21":1014,"_17":37,"_22":1015,"_24":1016,"_40":1017,"_42":1018,"_19":1014},"compositor/tools.mdx","Tools","All eight Compositor tools, their settings, gestures, and keyboard shortcuts.","","/docs/compositor/tools",{"_21":1020,"_17":37,"_22":1021,"_24":1022,"_40":1004,"_42":1023,"_19":1020},"compositor/layers.mdx","Layers","Every layer type the Compositor scene can hold and how each one behaves.","/docs/compositor/layers",{"_21":1025,"_17":37,"_22":1026,"_24":1027,"_40":1028,"_42":1029,"_19":1025},"compositor/properties.mdx","Properties","Canvas, transform, appearance, masks — the controls that shape what the scene renders.","","/docs/compositor/properties",{"_21":1031,"_17":58,"_40":-7,"_22":-7},"_11",{"_21":1033,"_17":37,"_22":1034,"_24":1035,"_40":1036,"_42":1037,"_19":1033},"compositor/timeline-and-export.mdx","Timeline & Export","Animate, scrub, and produce a final asset — image or video — from your composition.","","/docs/compositor/timeline-and-export","compositor","compositor/meta.json",{"_17":28,"_22":249,"_18":30,"_31":-7,"_24":1041,"_33":-7,"_25":1042,"_21":1079,"_19":1080,"_40":1046},"Programmable sketches on the canvas.",[1043,1048,1054,1059,1065,1067,1073],{"_21":1044,"_17":37,"_22":249,"_24":1045,"_40":1046,"_42":1047,"_19":1044},"creative-code/index.mdx","Programmable sketches that live on the canvas alongside every other node.","","/docs/creative-code",{"_21":1049,"_17":37,"_22":1050,"_24":1051,"_40":1052,"_42":1053,"_19":1049},"creative-code/prompting.mdx","Prompting and chat","Drive the Creative Code node from natural language with the prompt panel, chat history, and model picker.","","/docs/creative-code/prompting",{"_21":1055,"_17":37,"_22":1056,"_24":1057,"_40":1046,"_42":1058,"_19":1055},"creative-code/editor.mdx","Editing code by hand","The Creative Code editor — opening it, line-diff highlights, Explain this line.","/docs/creative-code/editor",{"_21":1060,"_17":37,"_22":1061,"_24":1062,"_40":1063,"_42":1064,"_19":1060},"creative-code/parameters-and-attachments.mdx","Parameters and inputs","Declare tunable controls with @fuser-params and connectable input sockets with @fuser-attachments.","","/docs/creative-code/parameters-and-attachments",{"_21":1066,"_17":58,"_40":-7,"_22":-7},"_12",{"_21":1068,"_17":37,"_22":1069,"_24":1070,"_40":1071,"_42":1072,"_19":1068},"creative-code/runtime.mdx","How sketches run","Supported libraries, the lifecycle, what's in scope, and what's blocked.","","/docs/creative-code/runtime",{"_21":1074,"_17":37,"_22":1075,"_24":1076,"_40":1077,"_42":1078,"_19":1074},"creative-code/publishing-and-export.mdx","Saving and sharing","Capture stills and recordings, navigate version history, and publish public embeds.","","/docs/creative-code/publishing-and-export","creative-code","creative-code/meta.json","fallback",{"_17":18,"_19":-7,"_21":1083,"_22":23,"_24":-7,"_25":1084},"fallback:root",[1085],{"_17":28,"_22":164,"_18":-7,"_31":-7,"_24":-7,"_33":-7,"_25":1086,"_21":1120,"_19":-7,"_40":-7},[1087,1096,1113],{"_17":28,"_22":190,"_18":-7,"_31":-7,"_24":-7,"_33":-7,"_25":1088,"_21":1095,"_19":-7,"_40":-7},[1089],{"_21":1090,"_17":37,"_22":1091,"_24":1092,"_40":416,"_42":1093,"_19":1094},"fallback:nodes/image/flux-1-krea-dev.mdx","FLUX.1 Krea [dev]","FLUX.1 Krea [dev] is the open weights version of Krea 1, offering strong performance with highly distinctive aesthetics and exceptional realism. It has been trained with the goal to generate more realistic and diverse images that do not contain oversaturated textures, a known issue in text-to-image generation. FLUX.1 Krea [dev] offers its users pleasant surprises in the form of diverse, visually interesting images. Despite its idiosyncrasies, FLUX.1 Krea [dev] outperforms previous open text-to-image models and is on par with closed solutions like FLUX1.1 [pro] in human preference assessments. Moreover it is architecturally compatible with the FLUX.1 [dev] ecosystem.","/docs/nodes/image/flux-1-krea-dev","nodes/image/flux-1-krea-dev.mdx","fallback:nodes/image",{"_17":28,"_22":1097,"_18":-7,"_31":-7,"_24":-7,"_33":-7,"_25":1098,"_21":1112,"_19":-7,"_40":-7},"Other",[1099,1105],{"_21":1100,"_17":37,"_22":1101,"_24":1102,"_40":914,"_42":1103,"_19":1104},"fallback:nodes/other/app.mdx","App","A live, AI-authored app — prompt to generate, iframe to preview.","/docs/nodes/other/app","nodes/other/app.mdx",{"_21":1106,"_17":37,"_22":1107,"_24":1108,"_40":1109,"_42":1110,"_19":1111},"fallback:nodes/other/resource.mdx","Resource","A durable backend service for Apps to call.","","/docs/nodes/other/resource","nodes/other/resource.mdx","fallback:nodes/other",{"_17":28,"_22":238,"_18":-7,"_31":-7,"_24":-7,"_33":-7,"_25":1114,"_21":1119,"_19":-7,"_40":-7},[1115],{"_21":1116,"_17":37,"_22":1117,"_24":1118,"_40":422,"_42":8,"_19":6},"fallback:nodes/video/luma-ray-2.mdx","Luma Ray 2","Ray2 is a large-scale video generative model capable of creating realistic visuals with natural, coherent motion.","fallback:nodes/video","fallback:nodes","imagePath","/og/docs/nodes/video/luma-ray-2/image.png","actionData","errors"]

Luma Ray 2

Preview

Inputs

Outputs

On this page