# Sloosh Docs

How to make images and video in Studio, run and build Spaces, and manage your plan and credits.

Web page: https://sloosh.ai/docs

## Explore

- [Start here](https://sloosh.ai/docs/first-generation.md): Open Studio, add an idea and make your first generation
- [Spaces](https://sloosh.ai/docs/spaces.md): Reusable creative workflows that make repeated work easy
- [Studio](https://sloosh.ai/docs/studio.md): The fastest path from prompt to image or video
- [Models](https://sloosh.ai/docs/models.md): Choose an image or video model based on the job

## Featured

- [Prompt guide](https://sloosh.ai/docs/prompt-guide.md): Good prompts are a brief, not a bag of keywords
- [Templates](https://sloosh.ai/docs/templates.md): Recreate a result that works, then make it yours
- [Generate video](https://sloosh.ai/docs/video-prompts.md): Describe the shot as a sequence with camera and pacing
- [Use references](https://sloosh.ai/docs/references.md): Give every reference a job: product, person, scene or style
- [Spacelab](https://sloosh.ai/docs/spacelab.md): Wire models into a workflow and publish it as a space
- [Plans and credits](https://sloosh.ai/docs/plans-and-credits.md): What each generation costs and how credits refill
- [Workspace and team](https://sloosh.ai/docs/workspace.md): Invite people, set roles and manage seats
- [MCP](https://sloosh.ai/docs/mcp.md): Bring creative workflows into tools your team uses

## Getting started

- [Your first generation](https://sloosh.ai/docs/first-generation.md): Make your first AI image or video in Sloosh in four steps: open Studio, describe what you want, check the chips and press Generate.
- [Help and support](https://sloosh.ai/docs/support.md): Fixes for the most common Sloosh problems: credits, billing, teams, failed or greyed-out generations, and where your results went.

## Studio

- [What is Studio](https://sloosh.ai/docs/studio.md): Studio is the quickest way from a prompt to an image or a video: write what you want, pick a model and press Generate.
- [Templates](https://sloosh.ai/docs/templates.md): A Sloosh template is a real image or video with the prompt and settings that made it. Press Recreate to load it into Studio, then make it yours.
- [Assets](https://sloosh.ai/docs/library.md): Sloosh Assets is your workspace library: Generations holds everything your workspace made, Elements holds the images and videos you keep to reuse.

## Prompt guide

- [Prompt guide](https://sloosh.ai/docs/prompt-guide.md): Write a Sloosh prompt as a brief, not a bag of keywords: say the subject, the setting, the look and where the image will be used.
- [Video prompts](https://sloosh.ai/docs/video-prompts.md): Write an AI video prompt as one shot: the scene, what moves in order, the camera move and the pace.
- [Prompting GPT Image](https://sloosh.ai/docs/prompting-gpt-image.md): GPT Image reads a prompt like a spec sheet. Name the result, lay out the frame, quote every word of text and list what must not change.
- [Prompting Nano Banana](https://sloosh.ai/docs/prompting-nano-banana.md): Nano Banana reads a prompt as a description of a scene. Write it in sentences, name the people and products you reuse, and refine one change at a time.
- [Prompting Gemini Omni](https://sloosh.ai/docs/prompting-gemini-omni.md): Gemini Omni makes one continuous shot of up to 10 seconds, with sound. Describe one moment, move the camera inside it, and hold products steady with reference images.

## References

- [References](https://sloosh.ai/docs/references.md): A reference shows a Sloosh model what words can't: your product, a person, a scene or a style. Give each one a job and name it in the prompt.
- [Tag with @](https://sloosh.ai/docs/tagging.md): Type @ in a prompt to name a picture, clip or sound: an element from your Assets in Studio or Spacelab, a reference wired into a Spacelab model, or a file you uploaded to a space's form.

## Models

- [Models](https://sloosh.ai/docs/models.md): Sloosh offers 11 image models and 15 video models. Compare what each is best for, its reference limit, resolution and clip length.

## Image models

- [Nano Banana 2](https://sloosh.ai/docs/nano-banana-2.md): Google's Nano Banana 2: the fast all-rounder, from 512px drafts to 4K.
- [Nano Banana Pro](https://sloosh.ai/docs/nano-banana-pro.md): Google's Nano Banana Pro: production quality with the best text and brand consistency.
- [Nano Banana Lite](https://sloosh.ai/docs/nano-banana-lite.md): Google's Nano Banana Lite: the fastest, cheapest image model, for 1K drafts.
- [GPT Image 2.5 Sunburst](https://sloosh.ai/docs/gpt-image-2-5-sunburst.md): OpenAI's most careful GPT Image 2.5 tier: slower, built for edits and detail that must survive a close look.
- [GPT Image 2.5 Flare](https://sloosh.ai/docs/gpt-image-2-5-flare.md): OpenAI's fast GPT Image 2.5 tier for everyday images and edits, including layouts with text.
- [GPT-image-2](https://sloosh.ai/docs/gpt-image-2.md): OpenAI's GPT-image-2: strong at following complex instructions, text and designed layouts.
- [FLUX 3 Image](https://sloosh.ai/docs/flux-3-image.md): Black Forest Labs' FLUX 3 Image: generate and edit up to 4K, with text in many languages.
- [Flux 2 Pro](https://sloosh.ai/docs/flux-2-pro.md): Black Forest Labs' FLUX.2 Pro: photoreal product scenes, exact hex colours and multi-reference composites.
- [Seedream 5 Pro](https://sloosh.ai/docs/seedream-5-pro.md): ByteDance's Seedream 5 Pro: precise region edits, text in many languages and multi-reference images.
- [Ideogram 4.5](https://sloosh.ai/docs/ideogram-4-5.md): Ideogram 4.5: typography that's spelled right and placed where you ask, and edits that leave the rest of the image untouched.
- [Meta Muse](https://sloosh.ai/docs/meta-muse.md): Meta Muse: plans its layout and checks its own drafts, with built-in world knowledge.

## Video models

- [Seedance 2.5](https://sloosh.ai/docs/seedance-2-5.md): Seedance 2.5 in Sloosh: ByteDance video of 4 to 30 seconds at up to 1080p, with 30 image and 10 video references, timed beats and sound.
- [Seedance 2.0](https://sloosh.ai/docs/seedance-2-0.md): Seedance 2.0 in Sloosh: ByteDance video with sound, 4 to 15 seconds at up to 4K, guided by up to 9 images and 3 videos.
- [Seedance 2.0 Fast](https://sloosh.ai/docs/seedance-2-0-fast.md): ByteDance's Seedance 2.0 Fast: the same features as 2.0 for less, at up to 720p.
- [Kling V3 Omni](https://sloosh.ai/docs/kling-v3-omni.md): Kling V3 Omni in Sloosh: Kuaishou video of 3 to 15 seconds at up to 4K, with 7 references, start and end frames and up to 6 shots.
- [Kling 3.0](https://sloosh.ai/docs/kling-3-0.md): Kling 3.0 in Sloosh: Kuaishou animates your start image into a 3 to 15 second clip with dialogue and optional sound.
- [Kling 2.5](https://sloosh.ai/docs/kling-2-5.md): Kling 2.5 Turbo in Sloosh: a quick, silent 5 or 10 second clip animated from one start image.
- [Veo 3.1](https://sloosh.ai/docs/veo-3-1.md): Veo 3.1 in Sloosh: Google's 8-second video with sound, up to 4K, with 3 references or start and end frames.
- [Gemini Omni 1.1 Flash](https://sloosh.ai/docs/gemini-omni-1-1-flash.md): Gemini Omni 1.1 Flash in Sloosh: Google video with sound, 3 to 10 seconds from 360p to 4K, with first and last frames.
- [Gemini Omni Flash](https://sloosh.ai/docs/gemini-omni-flash.md): Google's first Gemini Omni Flash: conversational video with sound at a fixed resolution.
- [MiniMax H3](https://sloosh.ai/docs/minimax-h3.md): MiniMax H3 in Sloosh: text or start-and-end-frame video with sound, 5 to 15 seconds at up to 4K, in six aspect ratios.
- [MiniMax H3 Max](https://sloosh.ai/docs/minimax-h3-max.md): MiniMax H3 Max in Sloosh: a faster H3 for text or start-and-end-frame video with sound, 5 to 15 seconds at up to 1080p.
- [MiniMax H3 Reference](https://sloosh.ai/docs/minimax-h3-reference.md): MiniMax H3 Reference in Sloosh: H3 video with sound guided by up to 9 reference images, 5 to 15 seconds at up to 4K.
- [MiniMax H3 Max Reference](https://sloosh.ai/docs/minimax-h3-max-reference.md): MiniMax H3 Max Reference: faster reference-guided H3 video, up to 1080p.
- [Grok Imagine](https://sloosh.ai/docs/grok-imagine.md): Grok Imagine in Sloosh: xAI reference-to-video with sound, 4 to 10 seconds at up to 720p, in seven aspect ratios, from up to 7 images.
- [Pruna P-Video 2 Pro](https://sloosh.ai/docs/p-video-2-pro.md): Pruna P-Video 2 Pro in Sloosh: fast video with sound from text or start and end frames, 5 to 15 seconds at 480p or 768p.

## Spaces

- [What is a space](https://sloosh.ai/docs/spaces.md): A space is a creative workflow behind a simple form. Fill in the inputs, press Generate and get the same kind of result every time.

## AI Influencer

- [AI Influencer](https://sloosh.ai/docs/ai-influencer.md): Build a character once, from tiles or from a photo, and put them in any video with Shadow Clone, with the same face, hair and outfit every time.

## Spacelab

- [What is Spacelab](https://sloosh.ai/docs/spacelab.md): Spacelab is the canvas where you build a space: wire inputs, models and edits together, test the flow, then publish it as a form anyone can run.
- [How Spacelab works](https://sloosh.ai/docs/how-spacelab-works.md): A canvas is nodes joined by wires. Inputs feed models, models feed edits, and whatever sits at the end of the flow is your result.
- [Input nodes](https://sloosh.ai/docs/nodes-input.md): Input nodes hold what a run starts from: text, images, video, audio and settings. When you publish, most of them become the space's form.
- [Generate nodes](https://sloosh.ai/docs/nodes-generate.md): Generate nodes call a model to make text, images, video or music. They cost credits each time they run.
- [Edit nodes](https://sloosh.ai/docs/nodes-edit.md): Edit nodes change something that already exists: a prompt, an image or a video. Several are free.
- [Output and tool nodes](https://sloosh.ai/docs/nodes-tools.md): Download at the end of a flow, the tools that loop, sort and pick, and notes for whoever opens the canvas next.
- [Spacelab recipes](https://sloosh.ai/docs/spacelab-recipes.md): Three canvases you can build in a few minutes, each a starting point for a space.

## MCP

- [MCP](https://sloosh.ai/docs/mcp.md): Connect Claude, ChatGPT, Cursor, VS Code or Codex to your Sloosh workspace over MCP to run spaces, generate and build canvases within a daily limit.

## Build with Sloosh

- [Build with Sloosh](https://sloosh.ai/docs/build.md): Put Sloosh inside your own product. This isn't available yet. (coming soon)

## API

- [API](https://sloosh.ai/docs/api.md): Create assets and start generations from your own code. The Sloosh API isn't live yet. (coming soon)

## Account & usage

- [Plans and credits](https://sloosh.ai/docs/plans-and-credits.md): Everything you make in Sloosh costs credits. Your plan sets how many you get and what you can make.
- [Workspace and team](https://sloosh.ai/docs/workspace.md): Your workspace holds your team, your credits and everything you make.