# Visual Sandbox

> Pay-per-use AI media platform. Generate images, video, audio, 3D,
> and vector art from a chat-style interface — no subscription, no API key.
> Top up once, every model is one click away.

- Home: https://visualsandbox.com/
- Pricing: https://visualsandbox.com/pricing/ (every model in credits; 1 credit = 1 cent)
- Image editor: https://visualsandbox.com/edit/
- Sitemap: https://visualsandbox.com/sitemap.xml

## In ChatGPT, Claude and other assistants

- General MCP URL: https://visualsandbox.com/mcp (OAuth sign-in or an API token)
- [MCP server setup](https://visualsandbox.com/mcp-server/)
- [Claude Code plugin](https://visualsandbox.com/claude-code/)
- [vsb CLI](https://visualsandbox.com/cli/)

## Imagine (text → image, image edit)

- [FLUX.2 Klein 9B — Black Forest Labs](https://visualsandbox.com/imagine/black-forest-labs/flux-2-klein-9b/): FLUX.2 Klein 9B is Black Forest Labs' high-fidelity distilled AI image model.
- [FLUX 3 Image Klein — Black Forest Labs](https://visualsandbox.com/imagine/black-forest-labs/flux-3-image-klein/): FLUX 3 Image Klein is the compact model of Black Forest Labs' FLUX 3 family.
- [FLUX Fill Pro — Black Forest Labs](https://visualsandbox.com/imagine/black-forest-labs/flux-fill-pro/): FLUX Fill Pro is Black Forest Labs' state-of-the-art AI inpainting and outpainting model.
- [Seedream 5 Lite — ByteDance](https://visualsandbox.com/imagine/bytedance/seedream-5-lite/): Seedream 5 Lite is ByteDance's fast AI image model for generation and editing.
- [Seedream 5 Pro — ByteDance](https://visualsandbox.com/imagine/bytedance/seedream-5-pro/): Seedream 5 Pro is ByteDance's flagship AI image model for generation and editing.
- [Nano Banana — Google](https://visualsandbox.com/imagine/google/nano-banana/): Nano Banana is Google's state-of-the-art AI image model.
- [Nano Banana 2 — Google](https://visualsandbox.com/imagine/google/nano-banana-2/): Nano Banana 2 is Google's next-generation AI image model.
- [Nano Banana 2 Lite — Google](https://visualsandbox.com/imagine/google/nano-banana-2-lite/): Nano Banana 2 Lite is Google's fastest AI image model.
- [Nano Banana 2.1 — Google](https://visualsandbox.com/imagine/google/nano-banana-2.1/): Nano Banana 2.1 is Google's fast, efficient AI image model.
- [Nano Banana Pro — Google](https://visualsandbox.com/imagine/google/nano-banana-pro/): Nano Banana Pro is Google's highest-fidelity AI image model.
- [Krea 2 Large — Krea](https://visualsandbox.com/imagine/krea/krea-2-large/): Krea 2 Large is Krea's flagship foundation image model.
- [Krea 2 Medium — Krea](https://visualsandbox.com/imagine/krea/krea-2-medium/): Krea 2 Medium is Krea's mid-size foundation image model.
- [Krea 3 — Krea](https://visualsandbox.com/imagine/krea/krea-3/): Krea 3 is Krea's instruction-following image editor.
- [GPT Image 2 — OpenAI](https://visualsandbox.com/imagine/openai/gpt-image-2/): GPT Image 2 is OpenAI's state-of-the-art AI image model.
- [GPT Image 2.5 Flare — OpenAI](https://visualsandbox.com/imagine/openai/gpt-image-2.5-flare/): GPT Image 2.5 Flare is OpenAI's fast image model.
- [GPT Image 2.5 Sunburst — OpenAI](https://visualsandbox.com/imagine/openai/gpt-image-2.5-sunburst/): GPT Image 2.5 Sunburst is OpenAI's precision image model.
- [P-Image Try-On — Pruna AI](https://visualsandbox.com/imagine/prunaai/p-image-try-on/): P-Image Try-On is Pruna AI's purpose-built virtual try-on model.
- [Z-Image Turbo — Tongyi-MAI](https://visualsandbox.com/imagine/prunaai/z-image-turbo/): Z-Image Turbo is Tongyi-MAI's sub-second AI image model.
- [Recraft V4.1 — Recraft](https://visualsandbox.com/imagine/recraft-ai/recraft-v4.1/): Recraft V4.1 is Recraft's design-minded AI image model.
- [Recraft V4.1 Flash — Recraft](https://visualsandbox.com/imagine/recraft-ai/recraft-v4.1-flash/): Recraft V4.1 Flash is Recraft's fastest and lowest-cost image model.
- [Grok Imagine 2.0 — xAI](https://visualsandbox.com/imagine/xai/grok-imagine-image-2/): Grok Imagine 2.0 is xAI's image model for generation and editing.

## Video (text → video, image → video)

- [Wan 3.0 — Alibaba](https://visualsandbox.com/video/alibaba/wan-3/): Wan 3.0 is Alibaba's state-of-the-art AI video model.
- [FLUX 3 — Black Forest Labs](https://visualsandbox.com/video/black-forest-labs/flux-3/): FLUX 3 is Black Forest Labs' state-of-the-art multimodal video model.
- [Seedance 2.0 — ByteDance](https://visualsandbox.com/video/bytedance/seedance-2.0/): Seedance 2.0 is ByteDance's state-of-the-art AI video model.
- [Seedance 2.0 Fast — ByteDance](https://visualsandbox.com/video/bytedance/seedance-2.0-fast/): Seedance 2.0 Fast is the speed tier of ByteDance's Seedance 2.0 video model.
- [Seedance 2.0 Mini — ByteDance](https://visualsandbox.com/video/bytedance/seedance-2.0-mini/): Seedance 2.0 Mini is the low-cost tier of ByteDance's Seedance 2.0 video model.
- [Seedance 2.5 — ByteDance](https://visualsandbox.com/video/bytedance/seedance-2.5/): Seedance 2.5 is ByteDance's state-of-the-art AI video model and the successor to Seedance 2.0.
- [Veo 3.1 — Google](https://visualsandbox.com/video/google/veo-3.1/): Veo 3.1 is Google DeepMind's flagship AI video model.
- [Veo 3.1 Fast — Google](https://visualsandbox.com/video/google/veo-3.1-fast/): Veo 3.1 Fast is the speed tier of Google DeepMind's Veo 3.1 video model.
- [Kling Avatar 2.0 — Kuaishou](https://visualsandbox.com/video/kuaishou/kling-avatar-v2/): Kling Avatar 2.0 is Kuaishou's state-of-the-art talking-head avatar model.
- [Kling 3.0 Motion Control — Kuaishou](https://visualsandbox.com/video/kuaishou/kling-v3-motion-control/): Kling 3.0 Motion Control transfers motion from a reference video onto a still character image.
- [Kling 3.0 Omni — Kuaishou](https://visualsandbox.com/video/kuaishou/kling-v3-omni-video/): Kling 3.0 Omni is Kuaishou's unified multimodal video model.
- [LTX 2.5 Fast — Lightricks](https://visualsandbox.com/video/lightricks/ltx-2.5-fast/): LTX 2.5 Fast is Lightricks' speed tier for open-weights AI video.
- [MiniMax H3 — MiniMax](https://visualsandbox.com/video/minimax/h3/): MiniMax H3 is MiniMax's state-of-the-art multimodal video model.
- [P-Video — Pruna AI](https://visualsandbox.com/video/prunaai/p-video/): P-Video is Pruna AI's purpose-built fast video model.
- [P-Video 2 — Pruna AI](https://visualsandbox.com/video/prunaai/p-video-2/): P-Video 2 is Pruna AI's quality-focused video model, the successor to P-Video.
- [P-Video 2 Pro — Pruna AI](https://visualsandbox.com/video/prunaai/p-video-2-pro/): P-Video 2 Pro is Pruna AI's highest-quality video model.
- [P-Video Animate — Pruna AI](https://visualsandbox.com/video/prunaai/p-video-animate/): P-Video Animate is Pruna AI's motion transfer model.
- [P-Video Avatar — Pruna AI](https://visualsandbox.com/video/prunaai/p-video-avatar/): P-Video Avatar is Pruna AI's purpose-built talking-head video model.
- [P-Video Edit — Pruna AI](https://visualsandbox.com/video/prunaai/p-video-edit/): P-Video Edit is Pruna AI's video editing model.
- [P-Video Replace — Pruna AI](https://visualsandbox.com/video/prunaai/p-video-replace/): P-Video Replace is Pruna AI's person swap model for video.
- [Lipsync 2 Pro — Sync](https://visualsandbox.com/video/sync/lipsync-2-pro/): Lipsync 2 Pro is Sync's studio-grade lip sync model.
- [Grok Imagine Video — xAI](https://visualsandbox.com/video/xai/grok-imagine-video/): Grok Imagine Video is xAI's video model with sound built in.
- [Grok Imagine Video 1.5 — xAI](https://visualsandbox.com/video/xai/grok-imagine-video-1.5/): Grok Imagine Video 1.5 is xAI's newer video model, and it animates a picture.

## Audio (sound effects, music)

- [Eleven Music — ElevenLabs](https://visualsandbox.com/audio/elevenlabs/eleven-music/): Eleven Music is ElevenLabs' state-of-the-art text-to-music model.
- [ElevenLabs Sound FX — ElevenLabs](https://visualsandbox.com/audio/elevenlabs/sound-effects-v2/): ElevenLabs Sound FX is ElevenLabs' state-of-the-art text-to-sound-effects model.
- [ElevenLabs Text to Speech — ElevenLabs](https://visualsandbox.com/audio/elevenlabs/text-to-speech/): ElevenLabs Text to Speech is ElevenLabs' state-of-the-art AI voice model.
- [ElevenLabs Voice Changer — ElevenLabs](https://visualsandbox.com/audio/elevenlabs/voice-changer/): ElevenLabs Voice Changer is ElevenLabs' state-of-the-art model for speaking a recording again in another voice.
- [ElevenLabs Voice Design — ElevenLabs](https://visualsandbox.com/audio/elevenlabs/voice-design/): ElevenLabs Voice Design is ElevenLabs' state-of-the-art model for creating a brand new voice from a written description.
- [ElevenLabs Voice Isolator — ElevenLabs](https://visualsandbox.com/audio/elevenlabs/voice-isolator/): ElevenLabs Voice Isolator takes the voice out of a recording and leaves the noise behind.
- [Gemini 3.8 Flash-Lite TTS — Google](https://visualsandbox.com/audio/google/gemini-3.8-flash-lite-tts/): Gemini 3.8 Flash-Lite TTS is Google's fast, cost-efficient text-to-speech model.
- [Gemini 3.8 Flash TTS — Google](https://visualsandbox.com/audio/google/gemini-3.8-flash-tts/): Gemini 3.8 Flash TTS is Google's flagship text-to-speech model.
- [MiniMax Music 2.6 — MiniMax](https://visualsandbox.com/audio/minimax/music-2.6/): MiniMax Music 2.6 is MiniMax's state-of-the-art text-to-music model.
- [MiniMax Music Cover — MiniMax](https://visualsandbox.com/audio/minimax/music-cover/): MiniMax Music Cover is MiniMax's AI cover song model.

## 3D (image → mesh)

- [Rodin Gen-2.5 — Hyper3D](https://visualsandbox.com/3d/hyper3d/rodin-gen-2.5/): Rodin Gen-2.5 is Hyper3D's state-of-the-art AI 3D model generator.
- [Meshy 7.1 — Meshy](https://visualsandbox.com/3d/meshy/meshy-7.1/): Meshy 7.1 is Meshy's state-of-the-art AI 3D model generator.
- [SAM 3D Objects — Meta](https://visualsandbox.com/3d/meta/sam-3-3d-objects/): SAM 3D Objects is Meta's AI 3D model generator, built for real photos.
- [TRELLIS 2 — Microsoft](https://visualsandbox.com/3d/microsoft/trellis-2/): TRELLIS 2 is Microsoft's open source AI 3D model generator.
- [Hunyuan 3D 3.1 — Tencent](https://visualsandbox.com/3d/tencent/hunyuan-3d-3.1/): Hunyuan 3D 3.1 is Tencent's state-of-the-art AI 3D model generator.
- [Tripo P2 — Tripo](https://visualsandbox.com/3d/tripo3d/tripo-p2/): Tripo P2 is Tripo's AI 3D model generator, built for games and real-time pipelines.

## Vector (text/image → SVG)

- [Quiver Arrow 2 — Quiver AI](https://visualsandbox.com/vector/quiver/arrow-2/): Quiver Arrow 2 is Quiver AI's state-of-the-art AI vector model.
- [Quiver Arrow 2 Telos — Quiver AI](https://visualsandbox.com/vector/quiver/arrow-2-telos/): Quiver Arrow 2 Telos is Quiver AI's deep-thinking AI vector model.
- [Recraft V4.1 SVG — Recraft](https://visualsandbox.com/vector/recraft-ai/recraft-v4.1-svg/): Recraft V4.1 SVG is Recraft's text-to-vector model.
- [Recraft Vectorize — Recraft](https://visualsandbox.com/vector/recraft-ai/recraft-vectorize/): Recraft Vectorize is Recraft's purpose-built raster-to-SVG converter.

## Tools

- [remove-background](https://visualsandbox.com/tool/remove-background/)
- [upscale](https://visualsandbox.com/tool/upscale/)
- [upscale](https://visualsandbox.com/tool/upscale/p-image-upscale/)
- [video-upscale](https://visualsandbox.com/tool/video-upscale/)
- [video-upscale](https://visualsandbox.com/tool/video-upscale/flux-video-upscale/)
- [video-upscale / starlight-fast-2](https://visualsandbox.com/tool/video-upscale/starlight-fast-2/)
- [video-upscale / starlight-precise-2.6](https://visualsandbox.com/tool/video-upscale/starlight-precise-2.6/)

## Compare

- [All comparisons](https://visualsandbox.com/compare/)
- [Visual Sandbox vs Krea](https://visualsandbox.com/compare/krea/): One resets your allowance every month. One does not.
- [Visual Sandbox vs Magnific](https://visualsandbox.com/compare/magnific/): One bundles a stock library. One sells you the run.
- [Visual Sandbox vs Higgsfield](https://visualsandbox.com/compare/higgsfield/): One sells a plan with unlimited days. One sells the run.
- [Visual Sandbox vs OpenArt](https://visualsandbox.com/compare/openart/): One prices the seat. One prices the run.
- [Visual Sandbox vs Melies](https://visualsandbox.com/compare/melies/): Both have a CLI. Only one bills by the month.
- [Visual Sandbox vs Lovart](https://visualsandbox.com/compare/lovart/): One is cheaper per image. One is free in a quiet month.
- [Visual Sandbox vs Morphic](https://visualsandbox.com/compare/morphic/): One tells stories on a timeline. One sells the run.
- [Visual Sandbox vs ArtCraft](https://visualsandbox.com/compare/artcraft/): One you download and own. One you open and pay per run.
- [Visual Sandbox vs Adventure AI](https://visualsandbox.com/compare/adventure-ai/): One keeps your credits. One never took a plan.
- [Visual Sandbox vs Kubeez](https://visualsandbox.com/compare/kubeez/): One replaces twelve subscriptions. One is not a subscription.
- [Visual Sandbox vs OneOver](https://visualsandbox.com/compare/oneover/): One bundles a chatbot. One sells the run.
- [Visual Sandbox vs Yapper](https://visualsandbox.com/compare/yapper/): One prices every model in credits. One prices it in cents.
- [Visual Sandbox vs Mitte](https://visualsandbox.com/compare/mitte/): One hands out credits by the thousand. One counts cents.
- [Visual Sandbox vs Magic](https://visualsandbox.com/compare/magic/): One sells templates. One sells the run.
- [Visual Sandbox vs InVideo AI](https://visualsandbox.com/compare/invideo/): One is an editor with a generator. One is a generator with a price.
- [Visual Sandbox vs Genspark](https://visualsandbox.com/compare/genspark/): One is an agent with a generator inside. One is a generator an agent can call.
- [Visual Sandbox vs Runway](https://visualsandbox.com/compare/runway/): One trained the model. One sells you the second.
- [Visual Sandbox vs Luma AI](https://visualsandbox.com/compare/luma/): One prices the second in credits. One prices it in cents.
- [Visual Sandbox vs Pika](https://visualsandbox.com/compare/pika/): One sells credits by the dollar. One sells the run for cents.
- [Visual Sandbox vs LTX Studio](https://visualsandbox.com/compare/ltx-studio/): One unlocks models by plan. One prices them all from the first cent.
- [Visual Sandbox vs Vidu](https://visualsandbox.com/compare/vidu/): One trained the model and sells the month. One sells the second.
- [Visual Sandbox vs Hedra](https://visualsandbox.com/compare/hedra/): One sells the character. One sells the second.
- [Visual Sandbox vs DomoAI](https://visualsandbox.com/compare/domoai/): One has a slow lane that is free. One has a fast lane that is priced.
- [Visual Sandbox vs HeyGen](https://visualsandbox.com/compare/heygen/): One sells the presenter. One sells the second.
- [Visual Sandbox vs Leonardo.Ai](https://visualsandbox.com/compare/leonardo/): One banks your tokens. One never issued any.
- [Visual Sandbox vs Ideogram](https://visualsandbox.com/compare/ideogram/): One is unlimited if you wait. One is priced if you do not.
- [Visual Sandbox vs Recraft](https://visualsandbox.com/compare/recraft/): One made the vectorizer. One sells it per SVG.
- [Visual Sandbox vs Meshy](https://visualsandbox.com/compare/meshy/): One sells a hundred meshes a month. One sells one mesh.
- [Visual Sandbox vs 3D AI Studio](https://visualsandbox.com/compare/3d-ai-studio/): Two aggregators. One sells the month, one sells the mesh.
- [Visual Sandbox vs Flora](https://visualsandbox.com/compare/flora/): One charges per seat. One charges per generation.
- [Visual Sandbox vs Figma Weave](https://visualsandbox.com/compare/figma-weave/): One sells credits by the month. One prints the price of a run.
- [Visual Sandbox vs ComfyUI](https://visualsandbox.com/compare/comfyui/): One you install and control. One you open and use.
- [Visual Sandbox vs Griptape](https://visualsandbox.com/compare/griptape-nodes/): One is a pipeline for a studio. One is a price for a run.
- [Visual Sandbox vs Kittl](https://visualsandbox.com/compare/kittl/): One is an editor with tokens. One is a generator with a price.
- [Visual Sandbox vs Glorify](https://visualsandbox.com/compare/glorify/): One is a design tool with AI on the side. One is the AI, priced.
- [Visual Sandbox vs MagicPath](https://visualsandbox.com/compare/magicpath/): One designs the screen. One makes what goes on it.
- [Visual Sandbox vs WaveSpeedAI](https://visualsandbox.com/compare/wavespeed/): Both charge per run. Both talk to agents. Only one has a canvas.
- [Visual Sandbox vs Lumenfall](https://visualsandbox.com/compare/lumenfall/): Both charge per run. One is an API. One is a place.

## Use cases

- [All use cases](https://visualsandbox.com/use-cases/): real results, each with what its run cost
- [Product photos from one photo](https://visualsandbox.com/use-cases/product-photos/): Start with one photo of your product. Get a studio shot and a new scene.
- [Animate a product photo](https://visualsandbox.com/use-cases/animate-a-product-photo/): Turn one still of your product into a short clip.
- [Vertical product video ads](https://visualsandbox.com/use-cases/product-video-ads/): A phone-style reel with sound, from one photo of your product.
- [A talking avatar from one portrait](https://visualsandbox.com/use-cases/talking-avatar/): Give a portrait a script. It talks to the camera.
- [One character in every shot](https://visualsandbox.com/use-cases/consistent-character/): Design a character once. It looks the same in each still and each clip.
- [Voiceovers](https://visualsandbox.com/use-cases/voiceovers/): Type a line, choose a voice, and get the read.

## Techniques

- [Techniques](https://visualsandbox.com/techniques/): both references, every group.

## Cinematic techniques

- [All techniques](https://visualsandbox.com/techniques/cinema/)
- [Shot types](https://visualsandbox.com/techniques/cinema/shot-types/): The ways to frame a shot, and the wording that gets each one.
- [Camera angles](https://visualsandbox.com/techniques/cinema/camera-angles/): Where to put the camera, and the wording that gets each angle.
- [Camera movement](https://visualsandbox.com/techniques/cinema/camera-movement/): The ways to move the camera, and the wording that gets each one.
- [Composition](https://visualsandbox.com/techniques/cinema/composition/): The ways to arrange a frame, and the wording that gets each one.
- [Lighting](https://visualsandbox.com/techniques/cinema/lighting/): The lighting setups, and the wording that gets each one.
- [Lenses and optics](https://visualsandbox.com/techniques/cinema/lenses/): The lenses, and the wording that gets the look of each one.
- [Aperture and f-stops](https://visualsandbox.com/techniques/cinema/aperture/): The f-stops, and what each one does to the background.
- [Format and body](https://visualsandbox.com/techniques/cinema/format-and-body/): The formats and cameras, and the wording that gets each one.
- [Colour and film look](https://visualsandbox.com/techniques/cinema/colour-grading/): The colour looks, and the wording that gets each one.
- [Time and motion](https://visualsandbox.com/techniques/cinema/time-and-motion/): The ways to bend time in a shot, and the wording for each one.
- [Cuts and transitions](https://visualsandbox.com/techniques/cinema/cuts-and-transitions/): The ways to get from one shot to the next.
- [In-camera and optical effects](https://visualsandbox.com/techniques/cinema/in-camera-effects/): The effects a camera can make on its own, and how to ask for them.
- [Atmosphere and weather](https://visualsandbox.com/techniques/cinema/atmosphere/): The ways to fill the air, and the wording that gets each one.
- [Genre looks](https://visualsandbox.com/techniques/cinema/genre-looks/): The genres, and the wording that gets the look of each one.
- [Viral looks](https://visualsandbox.com/techniques/cinema/viral-looks/): The looks that travel on short-form video, and how to ask for them.

## Print styles

- [All styles](https://visualsandbox.com/techniques/print/)
- [Graphic design movements](https://visualsandbox.com/techniques/print/design-movements/): The movements, and the wording that gets the look of each one.
- [Art movements as posters](https://visualsandbox.com/techniques/print/art-movements/): Each movement written as a poster the movement itself might have printed.
- [Print and reproduction looks](https://visualsandbox.com/techniques/print/print-processes/): The printing processes, and the wording for what each does to ink.
- [Handmade and folk](https://visualsandbox.com/techniques/print/handmade-and-folk/): Ways to make a poster that looks like a person made it, not a studio.
- [Place and era](https://visualsandbox.com/techniques/print/place-and-era/): National and period styles, each with the rules that made it local.
- [Propaganda and protest](https://visualsandbox.com/techniques/print/propaganda-and-protest/): Political traditions, and the visual rules each used to move people.
- [Music scenes](https://visualsandbox.com/techniques/print/music-scenes/): The scenes, and the graphic rules each used to say who a night was for.
- [Screen and digital](https://visualsandbox.com/techniques/print/screen-and-digital/): The looks that came from a screen, and the wording that gets each one.

## Drawing and render styles

- [All styles](https://visualsandbox.com/techniques/styles/)
- [Drawn traditions](https://visualsandbox.com/techniques/styles/drawn-traditions/): How a character is drawn by hand, and the wording that gets each tradition.
- [Anime and manga](https://visualsandbox.com/techniques/styles/anime-and-manga/): The looks from Japanese animation and comics, and the wording for each one.
- [Painted](https://visualsandbox.com/techniques/styles/painted/): The painting media, and the wording that gets each one out of a model.
- [Made by hand](https://visualsandbox.com/techniques/styles/made-by-hand/): Styles built from real material, and the wording that gets each one.
- [Rendered in 3D](https://visualsandbox.com/techniques/styles/rendered-in-3d/): How a computer model is made to look like something, and the wording.
- [Soft materials](https://visualsandbox.com/techniques/styles/soft-materials/): The surfaces that make a hard form soft, and the wording for each one.
- [Gradient and noise](https://visualsandbox.com/techniques/styles/gradient-and-noise/): How a colour transition is handled, and the wording for each one.
- [Applied over](https://visualsandbox.com/techniques/styles/applied-over/): Styles that put one thing on top of another, and the wording for each.
- [Character shapes](https://visualsandbox.com/techniques/styles/character-shapes/): How a figure is built and finished, and the wording for each decision.
- [Studio looks](https://visualsandbox.com/techniques/styles/studio-looks/): The looks asked for by studio name, described by what is on the screen.
- [Technical drawing](https://visualsandbox.com/techniques/styles/technical-drawing/): How a thing is specified rather than depicted, and the wording for each.

## Photography looks

- [All photography](https://visualsandbox.com/techniques/photography/)
- [Colour film stocks](https://visualsandbox.com/techniques/photography/colour-film/): The colour stocks, and what each does to skin, to sky and to green.
- [Black and white film stocks](https://visualsandbox.com/techniques/photography/black-and-white-film/): The stocks, and what each one does to grain, to skin and to the sky.
- [Slide and instant film](https://visualsandbox.com/techniques/photography/slide-and-instant/): The positive stocks, their narrow latitude, and the wording for each.
- [Camera and format](https://visualsandbox.com/techniques/photography/camera-and-format/): The ways to size a frame, and the wording that gets each one.
- [Darkroom and process](https://visualsandbox.com/techniques/photography/darkroom-and-process/): The changes made to the film itself, and the wording for each one.
- [Historical processes](https://visualsandbox.com/techniques/photography/historical-processes/): The processes from before the film roll, and the wording for each.
- [Photographic genres](https://visualsandbox.com/techniques/photography/photographic-genres/): Each genre written as the lens, the light and the distance that make it.
- [Product and commercial](https://visualsandbox.com/techniques/photography/product-and-commercial/): The shots a product needs, and the light, shadow and edge each takes.

## Colour palettes

- [All palettes](https://visualsandbox.com/techniques/colour/)
- [Colour harmony](https://visualsandbox.com/techniques/colour/harmony/): The ways to choose a set of colours, and the wording that gets each one.
- [Period palettes](https://visualsandbox.com/techniques/colour/period/): The sets of colours that date a picture, and the wording for each one.
- [Screen palettes](https://visualsandbox.com/techniques/colour/screen/): The palettes from film and television, and the wording for each one.
- [Nature and material](https://visualsandbox.com/techniques/colour/nature/): Palettes taken from landscapes and materials, with the words for each.
- [Functional palettes](https://visualsandbox.com/techniques/colour/functional/): Palettes chosen to do a job, with the real numbers behind them.

## Blog

- [All posts](https://visualsandbox.com/blog/)
- [How to pin an AI video's start and end frame](https://visualsandbox.com/blog/ai-video-start-and-end-frame/): Two photos control exactly how an AI video clip opens and closes, on Veo 3.1, Seedance 2.0, and Kling 3.0 Omni.
- [What AI Background Music Costs Per Track](https://visualsandbox.com/blog/what-ai-background-music-costs-per-track/): Eleven Music bills per second, not per month: $0.19 a minute. Here is what that beats against $10 to $30 monthly stock-music subscriptions.
- [What removing a photo background with AI costs](https://visualsandbox.com/blog/what-removing-a-photo-background-with-ai-costs/): Cutting a background out of a photo costs $0.02 on Visual Sandbox, flat. Competing tools charge by the month or up to a dollar a photo.
- [Make an AI image print-ready for ten cents](https://visualsandbox.com/blog/make-an-ai-image-print-ready-for-ten-cents/): Upscale on Visual Sandbox is a flat ten cents whether you double or quadruple a photo. Draft cheap, pick a winner, then spend the dime.
- [How to keep an AI character consistent across a shoot](https://visualsandbox.com/blog/keep-an-ai-character-consistent-across-a-shoot/): Re-prompting breaks a character's face. Reference images fix it. The workflow that keeps faces, outfits, and styling stable across a series.
- [How AI motion transfer turns a photo into a dancer](https://visualsandbox.com/blog/how-ai-motion-transfer-turns-a-photo-into-a-dancer/): AI motion transfer maps a dance from any video onto any character photo. Here's how the workflow behind viral AI dance trends actually works.
- [Text to SVG: three AI vector models and what they cost](https://visualsandbox.com/blog/ai-vector-models-what-svg-costs/): Three AI models turn text or images into SVG files on Visual Sandbox, from $0.02 to $0.44 each. Here is which one fits your project.
- [Turn any product photo into a talking spokesperson](https://visualsandbox.com/blog/turn-a-product-photo-into-a-talking-spokesperson/): One portrait and one audio clip is all an AI avatar needs to deliver your script. No camera, no actor, no studio day.
- [What an 8-second AI video clip actually costs](https://visualsandbox.com/blog/what-an-8-second-ai-video-clip-actually-costs/): Eight AI video models, eight different prices. Here is what an 8-second clip costs on each, from $0.08 to $12.56, with live per-second rates.
- [Make a launch poster with the model it announces](https://visualsandbox.com/blog/launch-poster-with-the-model-it-announces/): The Nano Banana 2 Lite launch image cost $0.05 and one prompt, made with Lite itself. The exact reference recipe and text trick inside.
- [AI image models that get text right (and what they cost)](https://visualsandbox.com/blog/ai-image-models-text-rendering/): Readable text is the hardest thing to get from an AI image model. Compare the five that do it well, with live per-image prices from $0.01.
- [Which Nano Banana model to use, and what it costs](https://visualsandbox.com/blog/which-nano-banana-model-to-use/): Google's Nano Banana 2 Lite lands at $0.05 an image. Here is when to use Lite, standard, or Pro, with real per-image prices.
- [New AI models drop weekly. Subscriptions can't keep up](https://visualsandbox.com/blog/new-ai-models-drop-weekly-subscriptions-cant-keep-up/): New AI models launch behind plan tiers and preview rings. Here is what launch week costs subscribers, and what trying a new model costs pay-per-use.