# Fuser

> Fuser is a node-based AI workflow builder on an infinite canvas, built for creative agencies and studio teams. Connect references, prompts and AI models, then keep the working process alongside the finished assets.

Fuser runs 290 image, video, audio and 3D model variants and 97 LLMs. Model pages are grouped by family (108 pages), so one page covers every version of a model, e.g. Veo 3 and Veo 3.1; each model line lists its versions, inputs → output, limits and credit cost.

Every link below is the markdown version of a fuser.studio page; drop the `.md` for the HTML page.

## Pages

- [About](https://fuser.studio/about.md): A story about what it means to create and to imagine in the age of intelligent tools.
- [Assembly](https://fuser.studio/assembly.md): Fuser Assembly is a global community of educators and creative practitioners who learn with Fuser, teach others, and earn through workshops, grants, and fellowships
- [Partners](https://fuser.studio/partners.md): Join Fuser's Community Partners network to earn 60% commissions through our referral program. Apply to host workshops and share resources with creative technologists and design studios.
- [Fuser pricing](https://fuser.studio/pricing.md): Monthly plans, credit packs, trial and Teams seats.

## Articles

- [Creative AI Guides: Models, Tools and Workflows](https://fuser.studio/articles.md): Practical Fuser guides to AI image models, image-to-video, product photography and node-based creative workflows.
- [AI Image Generation Glossary: 31 Terms Explained](https://fuser.studio/articles/ai-image-generation-glossary.md): Plain-English definitions of 31 AI image and video generation terms, from LoRA, ControlNet and CFG to inpainting, seeds, upscaling and image-to-video.
- [AI Storyboard to Animatic: A Node Workflow](https://fuser.studio/articles/ai-storyboard-to-animatic.md): Turn a shot list into consistent AI storyboard frames, then animate each board into a moving shot with start and end frames. A practical node workflow in Fuser.
- [Best AI 3D Model Generators (2026)](https://fuser.studio/articles/best-ai-3d-model-generators.md): Compare Hunyuan3D, Trellis 2, Tripo, Rodin, Meshy and SAM 3D for image-to-3D and text-to-3D. See one photo turned into three GLB models, plus remesh, retexture and rigging.
- [Best AI Avatar Video Generators: One Portrait, One Script, Four Models](https://fuser.studio/articles/best-ai-avatar-video-generators.md): We gave HeyGen Avatar IV, Veo 3.1, Kling 3.0 and MiniMax H3 the same portrait and the same two-sentence script. See all four talking clips, what each costs, and when to use Act-Two or Kling Motion Control instead.
- [AI Background Removers Tested: Bria RMBG 2.0 vs Rembg (2026)](https://fuser.studio/articles/best-ai-background-removers.md): We ran Bria RMBG 2.0 and Rembg on backlit curly hair and clear glassware. See the edge differences, what neither handles, and when to generate a transparent image or replace the background instead.
- [Best AI Image Editing Models (2026)](https://fuser.studio/articles/best-ai-image-editing-models.md): One photo, one edit instruction, seven models: GPT Image 2.5, Nano Banana 2, FLUX.2, FLUX.1 Kontext, Qwen Image 2, Seedream 5.0 Lite and Grok Imagine. See what each kept and changed.
- [Best AI Image Models for Creative Work (2026)](https://fuser.studio/articles/best-ai-image-models.md): Choose GPT Image, Gemini Image or Recraft for reference-led edits, campaign visuals and SVG assets. Build the complete creative workflow in Fuser.
- [Best AI Lip Sync Tools (2026): One Voice Line, Four Models](https://fuser.studio/articles/best-ai-lip-sync-tools.md): LatentSync, HeyGen Avatar IV, MiniMax H3 and Seedance 2.5 given the same face and the same voice line. See the real outputs, what each one changes, and which to use.
- [Best AI Logo and Vector Generators (2026): SVG vs PNG, Tested](https://fuser.studio/articles/best-ai-logo-and-vector-generators.md): One logo prompt through Recraft V4.1, GPT Image 2.5, Nano Banana 2 and Qwen Image 2. Which return a real SVG, which get the wordmark right, and how to hit exact brand colours.
- [Best AI Models for Text in Images (2026)](https://fuser.studio/articles/best-ai-models-for-text-in-images.md): We ran one poster prompt and one menu prompt through GPT Image 2.5, Nano Banana 2, Recraft V4.1, Qwen Image 2, Seedream 5.0 Lite and FLUX.2, then counted every correct character.
- [Best AI Music and Sound Effect Generators (2026)](https://fuser.studio/articles/best-ai-music-and-sound-effect-generators.md): Pick ElevenLabs for sound effects and voice, MMAudio or Mirelo to score silent AI video, MiniMax Music for songs from a reference track, and F5-TTS for voice cloning.
- [Best AI Product Photography Tools for Campaigns](https://fuser.studio/articles/best-ai-product-photography-tools.md): Compare Fuser, Photoroom, Krea and FLORA for product campaigns, catalog editing and reusable creative workflows. Keep product and brand details editable.
- [Best AI Upscalers for Images and Video (2026)](https://fuser.studio/articles/best-ai-upscalers.md): Choose Topaz, Recraft, ESRGAN or SeedVR by job: faithful photo enlargements, crisp graphics, generative texture rebuilding or 4K AI video. See a same-source 4x test.
- [Best AI Video Editing Models: Same Clip, Same Edits](https://fuser.studio/articles/best-ai-video-editing-models.md): Runway Aleph 2.0, Luma Ray 3.2, Grok Imagine Edit and Gemini Omni 1.1 Flash compared for editing existing footage, with a same-clip re-light and restyle test.
- [Best AI Video Generators With Audio: Same Dialogue Prompt, Seven Models](https://fuser.studio/articles/best-ai-video-generators-with-audio.md): Seven video models that make sound and speech in one pass, tested on one dialogue prompt: Veo 3.1, Kling 3.0, Seedance 2.5, Wan 2.6, Grok, MiniMax H3, LTX-2.5.
- [Best AI Virtual Try-On Models (2026)](https://fuser.studio/articles/best-ai-virtual-try-on.md): One model photo, one flat-lay shirt, five models: FASHN Try-On v1.6, Nano Banana 2, GPT Image 2.5 Flare, FLUX.2 [pro] and Qwen Image Edit. See what each kept, changed and got wrong.
- [Best Image-to-Video Models for Creative Work (2026)](https://fuser.studio/articles/best-image-to-video-models.md): Choose MiniMax H3, H3 Max, Kling 3.0 or Seedance 2.5 for your next moving shot. Connect references, motion direction and editable finishing in Fuser.
- [Best Node-Based AI Workflow Tools (2026)](https://fuser.studio/articles/best-node-based-ai-tools.md): Choose a node-based AI workflow tool for creative production: compare Fuser, FLORA, ComfyUI, Figma Weave, Krea Nodes and Magnific Spaces by the work you need to finish.
- [Best Open-Source Video Models (2026): Wan 2.2, MiniMax H3, LTX-2.5](https://fuser.studio/articles/best-open-source-video-models.md): Wan 2.2, MiniMax H3 and LTX-2.5 compared: what each license actually allows, the hardware each needs, and real same-prompt clips. Plus which popular models are not open.
- [How to Chain AI Models into One Creative Workflow](https://fuser.studio/articles/chain-ai-models-workflow.md): Chain image, video, audio and upscaling models into one repeatable workflow: which links work, how to pass outputs between models, and how to keep the result reusable.
- [ComfyUI Alternatives: 6 Options With No Local Setup (2026)](https://fuser.studio/articles/comfyui-alternatives.md): Compare ComfyUI alternatives by what you need: a hosted node canvas, editable design or open-source local control. Fuser, Weave, FLORA, Krea, Invoke and more.
- [How to Keep AI Characters Consistent Across Images and Video](https://fuser.studio/articles/consistent-characters-ai.md): Keep the same AI character across scenes and shots: build one reference, edit it into new scenes with reference-led models, then animate from those frames. A repeatable workflow.
- [ElevenLabs Sound Effects Prompt Guide: Describe, Time and Sync Your SFX](https://fuser.studio/articles/elevenlabs-sound-effects-guide.md): How to prompt ElevenLabs Sound Effects v2: describe the source, material and space, when to set duration, what prompt influence does, loops, and when MMAudio or Mirelo fit better.
- [How to Make AI Videos Longer: Extend, Chain and Multi-Shot](https://fuser.studio/articles/extend-ai-video-length.md): Make AI video longer than one generation: extend endpoints (Grok Imagine, FLUX.3), last-frame chaining into any image-to-video model, and multi-shot prompts. Real test clips.
- [Facebook Cover Photo Size 2026: Desktop and Mobile](https://fuser.studio/articles/facebook-cover-photo-size.md): Facebook Page covers need at least 400 × 150 px and load fastest at 851 × 315 px, but display at 16:9 on desktop and 2.4:1 on mobile. Here is how to design one file for both.
- [First and Last Frame Video: How to Generate a Clip Between Two Images](https://fuser.studio/articles/first-last-frame-video-guide.md): Which AI video models take a start and end frame, how to make a matching pair with an image model and an edit, and what Veo 3.1, Kling 3.0, Seedance 2.5 and MiniMax H3 did with the same pair.
- [FLUX.2 Prompt Guide: Structure, JSON Prompts, Hex Colours and References](https://fuser.studio/articles/flux-2-prompt-guide.md): How to prompt FLUX.2 [pro], [max], [flex], [dev], [klein] and turbo: word order, JSON prompts, hex colours, quoted text and multi-reference edits, tested on real outputs.
- [FLUX.2 vs Nano Banana 2: Same-Prompt Test](https://fuser.studio/articles/flux-2-vs-nano-banana.md): We ran identical prompts through FLUX.2 [pro] and Nano Banana 2 (Gemini 3.1 Flash Image): hex color, poster text, object layout and a label-preserving edit. Results and when to pick each.
- [FLUX.1 Kontext Editing Guide: Instructions, Identity and Iterative Edits](https://fuser.studio/articles/flux-kontext-editing-guide.md): How to edit images with FLUX.1 Kontext: how to word instructions, keep a face intact, swap text and chain edits, with real before/after outputs from Pro and Max.
- [Fuser Launches Recipes, Giving Creative Teams Prebuilt AI Workflows](https://fuser.studio/articles/fuser-studio-launches-recipes.md): Agencies and studio teams can start from a working creative process, bring their own inputs and adapt it on an infinite canvas.
- [GPT Image Prompt Guide: Structure, Text, Edits and Sizes (GPT Image 2.5)](https://fuser.studio/articles/gpt-image-prompt-guide.md): How to prompt GPT Image 2.5 Flare, Sunburst and GPT Image 2: labelled prompt sections, exact text in quotes, change-only edits, multi-image references, quality and sizes, with real outputs.
- [Grok Imagine Image 2.0 Guide: Prompts, Editing and Settings](https://fuser.studio/articles/grok-imagine-image-guide.md): How to prompt and edit with xAI's Grok Imagine Image 2.0: text in images, multi-image edits with <IMAGE_0> tags, quality and resolution settings, tested outputs.
- [Grok Imagine Video 1.5 Guide: Text, Image, Edit and Extend](https://fuser.studio/articles/grok-imagine-video-guide.md): How xAI's Grok Imagine Video 1.5 works in practice: text-to-video, image-to-video, reference images, editing and extending clips, native audio, with real test clips.
- [Higgsfield Alternatives: 6 Options by Creative Job (2026)](https://fuser.studio/articles/higgsfield-alternatives.md): Compare Higgsfield alternatives by the job you use it for: multi-model campaigns, node workflows, frontier video models, editing and stock-backed production.
- [Hunyuan3D Guide: Image to 3D, Low Poly Topology and Multiview](https://fuser.studio/articles/hunyuan3d-guide.md): How to use Tencent Hunyuan3D V3 and Hunyuan3D 2 Multiview: input images, generation types, face count, quad topology, PBR and GLB export, with real test meshes.
- [Instagram Post Sizes (2026): Feed, Story, Reel and Carousel](https://fuser.studio/articles/instagram-post-sizes.md): Instagram now supports 3:4 posts up to 1080 × 1440 px. Get 2026 sizes for feed posts, carousels, stories, reels and reel covers, with the safe zones the interface covers.
- [Kling 3.0 Motion Control Guide: Driving Video, Orientation Modes and Limits](https://fuser.studio/articles/kling-3-motion-control-guide.md): How Kling 3.0 Motion Control works: character image plus driving video, Video vs Image orientation, sound, Standard vs Pro, input limits and real test runs.
- [Kling 3.0 Prompt Guide: Formula, Camera Moves and 10 Examples](https://fuser.studio/articles/kling-3-prompt-guide.md): How to prompt Kling 3.0: a six-part formula, camera and dialogue syntax, 10 copyable prompts by genre, fixes for common failures and the settings that matter.
- [LinkedIn Banner Size (2026): Profile, Company and Event Covers](https://fuser.studio/articles/linkedin-banner-size.md): The LinkedIn banner size is 1584 × 396 px (4:1). Get the 2026 sizes for profile banners, Company Page covers, event covers and article images, plus how to design around the profile photo.
- [LTX-2.5 Guide: Fast vs Pro, Prompts, Audio and Retake](https://fuser.studio/articles/ltx-2-5-guide.md): How Lightricks' LTX-2.5 works in practice: Fast vs Pro, how to prompt single and multi-shot scenes, native audio, resolution and length limits, and retaking part of a clip. Real test clips.
- [LTX-2.5 vs Wan 2.6: Same Prompt, Same Start Frame](https://fuser.studio/articles/ltx-2-5-vs-wan-2-6.md): We ran LTX-2.5 Pro and Fast on the exact prompts and start frames we gave Wan 2.6. Side-by-side clips with sound, a verdict per test, prices per second and which one has open weights.
- [Luma Ray 3.2 Guide: Prompts, Keyframes, Loops and Reframe](https://fuser.studio/articles/luma-ray-3-2-guide.md): How to use Luma Ray 3.2: image-to-video prompts, start and end keyframes, seamless loops, reframing to 9:16 and video edit strength, with real test clips.
- [Meshy 7 vs Rodin Gen-2.5 vs Tripo 2.5: Same-Photo 3D Test](https://fuser.studio/articles/meshy-vs-rodin-vs-tripo.md): We sent one product photo to Meshy 7, Rodin Gen-2.5 and Tripo 2.5 with default settings. Polycount, texture maps, materials, time and cost, with renders of every mesh.
- [MiniMax H3 (Hailuo 3) Prompt Guide: Motion, Camera and Image-to-Video](https://fuser.studio/articles/minimax-h3-prompt-guide.md): How to prompt MiniMax H3 and H3 Max: motion and camera language, dialogue and sound, image-to-video, references, and what prompt expansion does, from real runs.
- [MiniMax H3 vs Kling 3.0: Same-Prompt Video Test](https://fuser.studio/articles/minimax-h3-vs-kling-3.md): We ran MiniMax H3 at 768p and 2K on the exact prompts we gave Kling 3.0 Pro. See the clips side by side, what each did with a camera move and a spoken line, and which to pick.
- [MiniMax Music Prompt Guide: Reference Songs, Lyric Formatting and Length](https://fuser.studio/articles/minimax-music-prompt-guide.md): How to prompt MiniMax Music: choosing the reference song, formatting lyrics with line breaks, pauses and ##, and controlling length, tested on five real generations.
- [Nano Banana Prompt Guide: Generate, Edit and Combine Images with Gemini](https://fuser.studio/articles/nano-banana-prompt-guide.md): How to prompt Nano Banana 2 and Nano Banana Pro: Google's prompt templates, one-change edits, multi-image references and text rendering, with real outputs.
- [Nano Banana 2 vs GPT Image 2.5: Same-Prompt Test in 5 Tasks](https://fuser.studio/articles/nano-banana-vs-gpt-image.md): We ran identical prompts through Nano Banana 2 and GPT Image 2.5 Flare for photoreal, text, product, editing and character work. See the outputs and a verdict per task.
- [How to Turn a Product Photo into a Video Ad with AI](https://fuser.studio/articles/product-photo-to-video-ad.md): Turn one product photo into a short video ad: stage the product in a scene, animate it, add sound and captions, and finish the end card. A step-by-step AI workflow.
- [Qwen Image Edit Guide: Text Edits, Object Edits and Camera Angles](https://fuser.studio/articles/qwen-image-edit-guide.md): How to edit images with Qwen: rewrite text on a label, swap or remove objects, and change the camera angle. Real before/after outputs and the settings that matter.
- [Recraft V4.1 Guide: Logos, SVG Vectors, Text and Brand Colors](https://fuser.studio/articles/recraft-v4-guide.md): How to use Recraft V4.1 for brand work: prompt structure, quoted text, SVG vector output, exact brand colours, and when Pro is worth it. Tested with real outputs.
- [Runway Act-Two Guide: Performance Capture From One Video](https://fuser.studio/articles/runway-act-two-guide.md): How Runway Act-Two transfers a filmed performance onto a character image or video: what carries over, how to shoot the driving clip, settings, limits and cost.
- [Runway Aleph 2.0 Guide: Edit a Video With a Prompt or One Frame](https://fuser.studio/articles/runway-aleph-2-guide.md): How to edit existing footage with Runway Aleph 2.0: the prompt pattern Runway recommends, restyle, relight, add, remove and reframe, the edited-frame workflow, settings and cost.
- [Seedance 2.5 Prompt Guide: Shots, Camera, Audio and References](https://fuser.studio/articles/seedance-2-5-prompt-guide.md): How to prompt Seedance 2.5 and 2.0: ByteDance's prompt order, Shot N and timestamp syntax, sound brackets for dialogue and effects, @Image references, and fixes, with real clips.
- [Seedance 2.5 vs Kling 3.0 vs Veo 3.1: Same-Prompt Test](https://fuser.studio/articles/seedance-vs-kling-vs-veo.md): We ran the same two prompts through Seedance 2.5, Kling 3.0 Pro and Veo 3.1 with matched settings. See the frames, what each model did and when to pick which.
- [Seedream 5.0 Lite Prompt Guide: Multi-Reference, Text and 4K, Tested](https://fuser.studio/articles/seedream-prompt-guide.md): How to prompt Seedream 5.0 Lite: sentence briefs, quoted text, Figure 1/2/3 multi-reference edits, aspect ratio in the prompt and 2K–4K output, with real test outputs.
- [Seedream 5.0 Lite vs Nano Banana 2: Same-Prompt Test](https://fuser.studio/articles/seedream-vs-nano-banana.md): Five identical prompts through Seedream 5.0 Lite and Nano Banana 2: label text, a menu, counting, hands and a product edit. See the outputs and which to use for each job.
- [Social Media Image Sizes (2026 Cheat Sheet)](https://fuser.studio/articles/social-media-image-sizes.md): Every 2026 social media image size in one place: LinkedIn, Instagram, YouTube, Facebook, X, TikTok and Pinterest, with safe zones and a workflow for exporting exact pixels.
- [Sora Alternatives: What to Use Now That Sora Is Shut Down (2026)](https://fuser.studio/articles/sora-alternatives.md): OpenAI removed Sora 2 from its app and API. Replacements by job: Veo 3.1 for dialogue, Kling 3.0 and Seedance 2.5 for cinematic shots, reference models for characters, Seedance 2.0 Mini for cost.
- [X (Twitter) Header Size 2026: 1500 × 500 Guide](https://fuser.studio/articles/twitter-header-size.md): The X (Twitter) header size is 1500 × 500 px (3:1). X may crop up to 60 px from the top and bottom and the profile photo covers the lower left. See safe zones, file limits and a workflow.
- [Veo 3.1 Prompt Guide: Dialogue, Sound and 10 Examples](https://fuser.studio/articles/veo-3-1-prompt-guide.md): How to prompt Google Veo 3.1: the prompt elements Google recommends, how to write dialogue and sound, 10 copyable prompts, frame and reference options and common fixes.
- [Vidu Q1 Reference Guide: Consistent Characters and Products from Up to 7 Images](https://fuser.studio/articles/vidu-reference-guide.md): How to use Vidu Q1 Reference: pick and prepare up to 7 reference images, write prompts that name each subject, set movement amplitude, and what our real test clips kept or lost.
- [Wan 2.6 Guide: Multi-Shot Video, Audio and Reference Clips](https://fuser.studio/articles/wan-2-6-guide.md): How Alibaba's Wan 2.6 works in practice: text-, image- and reference-to-video, timed multi-shot prompts, native dialogue, Wan 2.6 Image, and why 2.6 is not open weights. Real test clips.
- [YouTube Banner Size 2026: Dimensions and Safe Area](https://fuser.studio/articles/youtube-banner-size.md): The YouTube banner size is 2560 × 1440 px (min 2048 × 1152, max 6 MB). See the safe area that shows on every device, how TV, desktop and mobile crop it, and how to export one that fits.
- [YouTube Thumbnail Size (2026): 3840 × 2160 and Shorts](https://fuser.studio/articles/youtube-thumbnail-size.md): YouTube now recommends 3840 × 2160 px thumbnails (16:9), minimum 640 px wide, up to 50 MB on desktop and 2 MB on mobile. Get Shorts thumbnail sizes and a workflow for readable thumbnails.

## Compare

- [Compare Fuser: AI Creative Workflow Tools](https://fuser.studio/compare.md): Compare Fuser with FLORA, Figma Weave, ComfyUI, Krea and Magnific Spaces for editable design, reusable workflows and bespoke creative tools.
- [Fuser vs ComfyUI: Creative Workflows & Custom Tools](https://fuser.studio/compare/fuser-vs-comfyui.md): Keep generation, design revisions and the tools your studio builds in one shared process. Start with a working Recipe and shape it around the brief.
- [Fuser vs Figma Weave: Creative Workflows & Custom Tools](https://fuser.studio/compare/fuser-vs-figma-weave.md): Generate the campaign. Design the finish. Build the tools your team wishes it had. Fuser brings those jobs onto one connected creative canvas.
- [Fuser vs FLORA: A Creative Canvas for the Whole Brief](https://fuser.studio/compare/fuser-vs-flora.md): Choose Fuser for AI generation, editable design and bespoke creative tools on one canvas. Compare it with FLORA and try a product campaign workflow.
- [Fuser vs Krea Nodes: Creative Workflows & Custom Tools](https://fuser.studio/compare/fuser-vs-krea.md): The image is approved. Now comes the headline, the layout, the next campaign and the tool your team needs to make it all again. Keep that work connected in Fuser.
- [Fuser vs Magnific Spaces: Creative Workflows & Custom Tools](https://fuser.studio/compare/fuser-vs-magnific-spaces.md): Bring the brief onto a canvas where you can generate assets, keep designs editable and build bespoke tools around the way your studio works.

## Features

- [Features](https://fuser.studio/features.md): Connect AI generation, editable design, custom tools and team feedback. Build workflows around your studio with Fuser’s creative canvas.
- [Apps](https://fuser.studio/features/apps.md): Turn ideas, references, and generated assets into interactive websites. Build, edit, preview, and publish with Fuser Apps, right from your creative canvas.
- [Compositor](https://fuser.studio/features/compositor.md): Layer images, video, text, vectors, and 3D objects
- [Creative Code](https://fuser.studio/features/creative-code.md): A full creative coding environment built right into your canvas
- [Creative Workflows](https://fuser.studio/features/creative-workflows.md): Connect prompts, references, LLMs, and creative models on one canvas. Compare directions, develop images into video, and reuse your process as a Recipe.
- [Multiplayer & Collaboration](https://fuser.studio/features/multiplayer.md): Create together on a shared canvas. See teammates at work, keep feedback beside the creative work, and control who can view, comment, or edit in Fuser.
- [Prompt Crafter](https://fuser.studio/features/prompt-crafter.md): Give your next generation clearer direction. Fuser Prompt Crafter uses node context to refine your brief, with an editable prompt you can review before running.
- [Recipes](https://fuser.studio/features/recipes.md): Find a creative workflow, make it your own, and run it again. Fuser Recipes turn connected nodes into reusable tools with clear inputs and outputs.
- [Teams](https://fuser.studio/features/teams.md): A generative workspace for your whole creative studio. Collaborate with your team in Fuser.

## Legal

- [Community Guidelines](https://fuser.studio/legal/community-guidelines.md): The rules and expectations for being part of the Fuser community.
- [Cookie Policy](https://fuser.studio/legal/cookies.md): Learn how Fuser uses cookies and similar technologies, why we use them, and how you can manage your cookie preferences.
- [Data Processing Agreement](https://fuser.studio/legal/dpa.md): Fuser's Data Processing Agreement for business customers.
- [Privacy Policy](https://fuser.studio/legal/privacy.md): How Fuser collects, uses, and protects your personal data.
- [Privacy FAQ](https://fuser.studio/legal/privacy-faq.md): Answers to the data-protection and procurement questions businesses ask about Fuser.
- [Sub-Processors](https://fuser.studio/legal/sub-processors.md): The service providers Fuser uses to operate the Service, and what each one does.
- [Terms of Service](https://fuser.studio/legal/terms.md): The terms and conditions that govern your use of Fuser.

## Models

- [Models](https://fuser.studio/models.md)
- [AnimateDiff](https://fuser.studio/models/animatediff.md): text, video → video · 9–35 credits per run
- [Auto Caption](https://fuser.studio/models/auto-caption.md): video → video · 138 credits per run
- [Background Remover](https://fuser.studio/models/background-remover.md): image → image · 25 credits per run
- [Background Replacer](https://fuser.studio/models/background-replacer.md): image, text → image · 55 credits per run
- [Bria Product Shot](https://fuser.studio/models/bria-product-shot.md): image, text → image · 55 credits per run
- [Canny Edge Detection](https://fuser.studio/models/canny-edge-detection.md): image → image · 2 credits per run
- [ChatGPT](https://fuser.studio/models/chatgpt.md): gpt-5.4, gpt-5.2, gpt-5.1, gpt-5 · text → text
- [Claude Chat](https://fuser.studio/models/claude-chat.md): claude-opus-4-7, claude-opus-4-6, claude-opus-4-5, claude-sonnet-4-6 · text → text
- [Cohere Chat](https://fuser.studio/models/cohere-chat.md): command-a, command-r7b, command-r, command-r-plus · text → text
- [DeepSeek Chat](https://fuser.studio/models/deepseek-chat.md): deepseek-chat, deepseek-reasoner · text → text
- [Depth Anything V2](https://fuser.studio/models/depth-anything-v2.md): image → image · 7 credits per run
- [ElevenLabs SFX](https://fuser.studio/models/elevenlabs-sfx.md): text → audio · 1–61 credits per run
- [ElevenLabs TTS](https://fuser.studio/models/elevenlabs-tts.md): text → audio · 3 credits per run
- [ESRGAN Upscaler](https://fuser.studio/models/esrgan-upscaler.md): Standard (4x upscaling), Standard (2x upscaling), Anime (4x upscaling), ESRGAN Upscaler V3 (4x upscaling) · image → image · 2 credits per run
- [F5 TTS](https://fuser.studio/models/f5-tts.md): F5-TTS (Better quality, slower), E2-TTS (Faster, lower quality) · text, audio → audio · 1 credits per run
- [Fashn Tryon](https://fuser.studio/models/fashn-tryon.md): image → image · 103 credits per run
- [Fast LCM Image Generator](https://fuser.studio/models/fast-lcm-image-generator.md): SDXL (Better quality, slower), SD v1.5 (Faster, lower quality) · text → image · 4 credits per run
- [Fast SDXL](https://fuser.studio/models/fast-sdxl.md): text → image · 7 credits per run
- [Fast SVD Video Generator](https://fuser.studio/models/fast-svd-video-generator.md): text → video · 69 credits per run
- [Florence-2 Image Captioner](https://fuser.studio/models/florence-2-image-captioner.md): image → text · 4 credits per run
- [FLUX.1 [Dev]](https://fuser.studio/models/flux-1-dev.md): text, image → image · 35–48 credits per run
- [FLUX.1 Kontext](https://fuser.studio/models/flux-1-kontext.md): Pro, Max · text, image → image · up to 110 credits per run
- [FLUX.2](https://fuser.studio/models/flux-2.md): Turbo, Dev, Pro, Max · text, image → image · 14–452 credits per run
- [FLUX.3](https://fuser.studio/models/flux-3.md): text, image, video → video · 5–20 seconds · up to 1080p · audio · 413–14,603 credits per run
- [FLUX1.1 [Pro] Ultra](https://fuser.studio/models/flux1-1-pro-ultra.md): text → image · 83 credits per run
- [Gemini Image](https://fuser.studio/models/gemini-image.md): Nano Banana (Gemini 2.5 Flash), Nano Banana 2 (Gemini 3.1 Flash), Nano Banana 2 Lite (Gemini 3.1 Flash Lite), Nano Banana Pro (Gemini 3 Pro) · text, image → image · up to 4K · 47–364 credits per run
- [Gemini Omni Video](https://fuser.studio/models/gemini-omni-video.md): text, image, video → video · 3–10 seconds · up to 4K · 58–8,223 credits per run
- [Google Gemini Chat](https://fuser.studio/models/google-gemini-chat.md): gemini-3.5-flash, gemini-3-flash-preview, gemini-3.1-pro-preview, gemini-3-pro-preview · text → text, image
- [GPT Image](https://fuser.studio/models/gpt-image.md): GPT Image 2.5 Flare, GPT Image 2.5 Sunburst, GPT Image 2, GPT Image 1.5 · text, image → image · 7–552 credits per run
- [Grok Imagine](https://fuser.studio/models/grok-imagine.md): Grok Imagine 1.5, Grok Imagine 1.0 · text, image → video · 1–15 seconds · up to 1080p · up to 5,166 credits per run
- [Grok Imagine Edit](https://fuser.studio/models/grok-imagine-edit.md): text, video → video · 2–10 seconds · up to 720p · 83–6,613 credits per run
- [Grok Imagine Image](https://fuser.studio/models/grok-imagine-image.md): text, image → image · up to 2K · 55–124 credits per run
- [Groq Chat](https://fuser.studio/models/groq-chat.md): openai/gpt-oss-20b, openai/gpt-oss-120b, qwen/qwen3-32b, llama-3.1-8b-instant · text → text
- [Hailuo 02](https://fuser.studio/models/hailuo-02.md): Fast (Image to Video), Standard, Pro · text, image → video · 6–10 seconds · up to 768p · 141–661 credits per run
- [Hailuo 2.3](https://fuser.studio/models/hailuo-2-3.md): Pro Fast, Standard Fast, Standard, Pro · text, image → video · 6–10 seconds · 265–772 credits per run
- [HED Edge Detection](https://fuser.studio/models/hed-edge-detection.md): image → image · 5 credits per run
- [HeyGen](https://fuser.studio/models/heygen.md): image, audio, text → video · up to 1080p · 138–8,266 credits per run
- [Hunyuan Motion](https://fuser.studio/models/hunyuan-motion.md): text → 3D model · 0.5–12 seconds · 110 credits per run
- [Hunyuan3D Multiview](https://fuser.studio/models/hunyuan3d-multiview.md): image → 3D model · 21–24 credits per run
- [Hunyuan3D V3](https://fuser.studio/models/hunyuan3d-v3.md): text, image → 3D model · 517–1,033 credits per run
- [Ideogram v2](https://fuser.studio/models/ideogram-v2.md): text, image → image · 110 credits per run
- [Kling 1.6 Video](https://fuser.studio/models/kling-1-6-video.md): Photorealistic cinematic scenes with physical weight, natural light physics, and seamless camera choreography
- [Kling 2.X Video Tool](https://fuser.studio/models/kling-2-x-video-tool.md): Kling 2.6 Pro, Kling 2.5 Turbo Standard, Kling 2.5 Turbo Pro · text, image → video · 5, 10 · audio · 289–1,929 credits per run
- [Kling 3.0 Motion](https://fuser.studio/models/kling-3-0-motion.md): Standard, Pro · text, image, video → video · 174–13,887 credits per run
- [Kling 3.0 Video](https://fuser.studio/models/kling-3-0-video.md): Standard, Pro · text, image → video · 3–15 seconds · audio · 347–3,472 credits per run
- [Krea](https://fuser.studio/models/krea.md): Krea 2, FLUX.1 Krea [dev] · text, image → image · 35–83 credits per run
- [LatentSync](https://fuser.studio/models/latentsync.md): video, audio → video · 689 credits per run
- [LTX](https://fuser.studio/models/ltx.md): text → video · up to 720p · 55 credits per run
- [LTX 2.5](https://fuser.studio/models/ltx-2-5.md): Fast, Pro · text, image, video → video · 6–20 seconds · up to 2160p · audio · 744–8,266 credits per run
- [LTX Extend](https://fuser.studio/models/ltx-extend.md): text, video → video · up to 720p · 55 credits per run
- [Lucy](https://fuser.studio/models/lucy.md): text, image → video · 331 credits per run
- [Luma Ray](https://fuser.studio/models/luma-ray.md): Ray 3.2, Ray 2, Ray 2 Flash · text, image, video → video · 5–10 seconds · up to 1080p · up to 17,854 credits per run
- [Luma Uni-1](https://fuser.studio/models/luma-uni-1.md): text, image → image · 58 credits per run
- [Luma Video](https://fuser.studio/models/luma-video.md): text, image → video · 689 credits per run
- [Meshy](https://fuser.studio/models/meshy.md): Meshy 5, Meshy 6, Meshy 7 · image, text → 3D model · up to 1,653 credits per run
- [Meshy 5 Remesh](https://fuser.studio/models/meshy-5-remesh.md): 3D model → 3D model · 276 credits per run
- [Meshy 5 Retexture](https://fuser.studio/models/meshy-5-retexture.md): 3D model, text, image → 3D model · 413 credits per run
- [Meshy Rigging](https://fuser.studio/models/meshy-rigging.md): 3D model → 3D model · 276–441 credits per run
- [MiniMax H3](https://fuser.studio/models/minimax-h3.md): H3, H3 Max · text, image, video, audio → video · 5–15 seconds · up to 4K · 345–3,306 credits per run
- [Minimax Music](https://fuser.studio/models/minimax-music.md): text, audio → audio · 48 credits per run
- [Mirelo SFX](https://fuser.studio/models/mirelo-sfx.md): video, text → video · 1–60 seconds · 7–1,653 credits per run
- [Mistral Chat](https://fuser.studio/models/mistral-chat.md): ministral-3b-latest, ministral-8b-latest, mistral-large-latest, mistral-small-latest · text → text
- [MLSD Line Detection](https://fuser.studio/models/mlsd-line-detection.md): image → image · 5 credits per run
- [MMAudio](https://fuser.studio/models/mmaudio.md): text, video → audio, video · 1–30 seconds · 1–41 credits per run
- [Moondream](https://fuser.studio/models/moondream.md): image, text → text · 7 credits per run
- [Moondream Detection](https://fuser.studio/models/moondream-detection.md): image, text → image, text · 7 credits per run
- [Muse Image](https://fuser.studio/models/muse-image.md): text, image → image · 14 credits per run
- [OpenRouter Chat](https://fuser.studio/models/openrouter-chat.md): text → text
- [Perplexity Chat](https://fuser.studio/models/perplexity-chat.md): sonar, sonar-pro, sonar-reasoning, sonar-reasoning-pro · text → text
- [Pika](https://fuser.studio/models/pika.md): text, image → video · 5–10 seconds · up to 1080p · 276–1,240 credits per run
- [Qwen Edit Angles](https://fuser.studio/models/qwen-edit-angles.md): image, text → image · 52 credits per run
- [Qwen-Image](https://fuser.studio/models/qwen-image.md): text, image → image · 28–41 credits per run
- [Qwen Image 2](https://fuser.studio/models/qwen-image-2.md): Standard, Pro · text, image → image · 48–103 credits per run
- [Qwen-Image Edit](https://fuser.studio/models/qwen-image-edit.md): text, image → image · 52 credits per run
- [Recraft Upscale](https://fuser.studio/models/recraft-upscale.md): image → image · 6 credits per run
- [Recraft v3](https://fuser.studio/models/recraft-v3.md): text, image → image · 55–110 credits per run
- [Recraft V4](https://fuser.studio/models/recraft-v4.md): Normal, Pro · text → image · 55–413 credits per run
- [Rembg](https://fuser.studio/models/rembg.md): image → image · 9 credits per run
- [Reve](https://fuser.studio/models/reve.md): Reve 2.1, Original · text, image → image · up to 345 credits per run
- [Rodin](https://fuser.studio/models/rodin.md): Rodin 2.5, Original · text, image → 3D model · 138–1,102 credits per run
- [Runway Act-Two](https://fuser.studio/models/runway-act-two.md): video, image → video · 69–4,133 credits per run
- [Runway Aleph](https://fuser.studio/models/runway-aleph.md): text, video, image → video · 772–23,144 credits per run
- [Runway Video](https://fuser.studio/models/runway-video.md): Gen-4 Turbo, Gen-4.5 · text, image → video · 5–10 seconds · 345–1,653 credits per run
- [SAM 3D Objects](https://fuser.studio/models/sam-3d-objects.md): image, text → 3D model · 28 credits per run
- [Scribble Detection](https://fuser.studio/models/scribble-detection.md): Holistically-Nested Edge Detection, PiDi · image → image · 5 credits per run
- [SDXL Canny Controlnet](https://fuser.studio/models/sdxl-canny-controlnet.md): text, image → image · 7 credits per run
- [SDXL Inpainting](https://fuser.studio/models/sdxl-inpainting.md): image, text → image · 7 credits per run
- [Seedance](https://fuser.studio/models/seedance.md): Pro v1.5, Lite, Pro Fast, Pro · text, image → video · 3–12 seconds · up to 1080p · audio · up to 2,064 credits per run
- [Seedance 2](https://fuser.studio/models/seedance-2.md): Seedance 2.5, Seedance 2.0, Seedance 2.0 Fast, Seedance 2.0 Mini · text, image, video, audio → video · 4–30 seconds · up to 4K · audio · up to 64,275 credits per run
- [Seedream](https://fuser.studio/models/seedream.md): text, image → image · 48 credits per run
- [SeedVR Upscale](https://fuser.studio/models/seedvr-upscale.md): video → video · 857–85,699 credits per run
- [Skin Enhancer](https://fuser.studio/models/skin-enhancer.md): text, image → image · 44 credits per run
- [Sora 2](https://fuser.studio/models/sora-2.md): Direct cinematic scenes with physical world accuracy and natively synchronized audio and dialogue
- [Topaz Image Upscale](https://fuser.studio/models/topaz-image-upscale.md): Standard V2, High Fidelity V3, High Fidelity V2, Low Resolution V2 · image, text → image · up to 7,313 credits per run
- [Topaz Upscale](https://fuser.studio/models/topaz-upscale.md): video → video · 14–6,613 credits per run
- [Trellis 2](https://fuser.studio/models/trellis-2.md): image → 3D model · 345–482 credits per run
- [Tripo 3D](https://fuser.studio/models/tripo-3d.md): image → 3D model · 276–620 credits per run
- [Veed Subtitles](https://fuser.studio/models/veed-subtitles.md): video, text → video · 138–276 credits per run
- [Veo](https://fuser.studio/models/veo.md): Veo 3.1 Fast, Veo 3.1, Veo 3 Fast, Veo 3 · text, image → video · 4–8 seconds · up to 1080p · audio · 551–4,409 credits per run
- [Vidu](https://fuser.studio/models/vidu.md): Vidu Q2, Vidu Q1, Vidu · text, image → video · 4–8 seconds · up to 1080p · up to 1,515 credits per run
- [Vidu Reference](https://fuser.studio/models/vidu-reference.md): Vidu Q1, Vidu · text, image → video · 551 credits per run
- [Wan-2.2 Image](https://fuser.studio/models/wan-2-2-image.md): Lite (5B), Pro (14B) · text → image · 22–35 credits per run
- [Wan-2.2 Video](https://fuser.studio/models/wan-2-2-video.md): Lite (5B), Pro (14B) · text, image, video → video · up to 720p · up to 2,667 credits per run
- [Wan 2.6 Image](https://fuser.studio/models/wan-2-6-image.md): text, image → image · 41 credits per run
- [Wan-2.6 Video](https://fuser.studio/models/wan-2-6-video.md): text, image, video, audio → video · 5–15 seconds · up to 1080p · 689–3,100 credits per run
- [Whisper](https://fuser.studio/models/whisper.md): audio → text · 35 credits per run
- [Z-Image](https://fuser.studio/models/z-image.md): text, image → image · up to 2K · 7–44 credits per run
- [Zoe Depth Map](https://fuser.studio/models/zoe-depth-map.md): image → image · 10 credits per run

## Solutions

- [Solutions](https://fuser.studio/solutions.md): Create campaign imagery, brand systems, video concepts and live web experiences. Connect AI generation with editable design in Fuser’s creative workspace.
- [Industries & teams](https://fuser.studio/solutions/industries.md): See how ecommerce, agencies, startups, fashion, film, games and architecture teams can use Fuser for their creative work.
- [Architecture & interiors](https://fuser.studio/solutions/industries/architecture-interiors.md): Explore interior moods, material palettes and architectural concepts. Turn room references and sketches into clear client presentation boards in Fuser.
- [Creative agencies](https://fuser.studio/solutions/industries/creative-agencies.md): Develop pitches, campaign assets and interactive client work in Fuser. Combine AI generation, editable design and reusable processes across your agency.
- [Ecommerce](https://fuser.studio/solutions/industries/ecommerce.md): Create product images, lifestyle scenes and campaign assets for your next ecommerce launch. Keep branding editable and reuse creative setups in Fuser.
- [Fashion & apparel](https://fuser.studio/solutions/industries/fashion-apparel.md): Develop on-person garment imagery, editorial concepts and lookbook layouts. Bring collection references, virtual try-on and editable design together in Fuser.
- [Film & animation](https://fuser.studio/solutions/industries/film-animation.md): Develop film treatments, character and environment concepts, storyboards and motion studies. Connect image, video and 3D exploration in Fuser.
- [Game development](https://fuser.studio/solutions/industries/game-development.md): Explore game characters, props and environments, develop 3D starting points and build playable web experiments. Shape your game’s art direction in Fuser.
- [Startups & product teams](https://fuser.studio/solutions/industries/startups-product-teams.md): Build working product demos, launch pages and brand visuals in Fuser. Help a small startup team turn the next idea into something people can try.
- [Use cases](https://fuser.studio/solutions/use-cases.md): Explore seven ways to use Fuser: moodboards, brand identity, product visuals, ads, social content, storyboards and interactive product prototypes.
- [Ad & campaign creative](https://fuser.studio/solutions/use-cases/ad-campaign-creative.md): Develop campaign concepts, image and video ads, and editable channel layouts. Create meaningful creative variations in Fuser without rebuilding every asset.
- [Brand identity & systems](https://fuser.studio/solutions/use-cases/brand-identity-systems.md): Explore a brand’s visual identity, refine typography and build real applications. Combine AI imagery with editable design and reusable workflows in Fuser.
- [Concepting & moodboards](https://fuser.studio/solutions/use-cases/concepting-moodboards.md): Turn a creative brief into distinct visual concepts, moodboards and pitch layouts. Explore references, imagery and motion together in Fuser.
- [Product design & prototyping](https://fuser.studio/solutions/use-cases/product-design-prototyping.md): Turn a UI or UX idea into a working web prototype. Create its visual assets, refine the interaction and share a live Fuser App for feedback.
- [Product visualization](https://fuser.studio/solutions/use-cases/product-visualization.md): Create studio-style product images, lifestyle scenes and motion studies. Combine reference-led generation with precise, editable composition in Fuser.
- [Social content](https://fuser.studio/solutions/use-cases/social-content.md): Create social graphics, carousel artwork and short videos with a recognizable brand style. Keep copy editable and recurring content easier to produce in Fuser.
- [Video & storyboards](https://fuser.studio/solutions/use-cases/video-storyboards.md): Develop storyboard frames, shot variations and video studies from your references. Compose clear boards and explore movement in one Fuser project.

## Recipes

- [Recipe index](https://fuser.studio/recipes/llms.txt): every public recipe with its inputs, outputs and FAQ, each with a markdown version.

## Docs

- [Fuser docs index](https://docs.fuser.studio/llms.txt): product documentation, one link per page.

- [Fuser docs, full text](https://docs.fuser.studio/llms-full.txt): every docs page in one file, including each node's inputs and outputs.

## Optional

- [Every fuser.studio page in full](https://fuser.studio/llms-full.txt): all of the pages above as one markdown file.