-
Notifications
You must be signed in to change notification settings - Fork 0
CLI Quickstart
h-avoyan edited this page Jun 18, 2026
·
1 revision
The gen-ai CLI is one terminal command for the entire model catalog. It's designed for piping and automation: anything the web app can do is scriptable.
npm install -g @picsart/gen-ai # or the install script — see Installation
gen-ai login # one-time browser auth# Image
gen-ai generate -m flux-2-pro -p "studio shot of a ceramic cup, soft light" --ar 4:3
# Video (text-to-video)
gen-ai generate -m seedance-2.0 -p "a fox running through autumn leaves" -d 8
# Audio (text-to-speech)
gen-ai generate -m eleven-v3 -p "Welcome to Picsart AI Playground."By default the CLI submits the job, shows a progress bar, prints the result URL, and downloads the file to ./output.
Run a command with no flags to get a guided wizard (mode → model picker → params):
gen-ai generate # walks you through everything
gen-ai # launch the REPL with a numbered menu# Pipe a prompt from stdin
echo "a neon city flyover at dusk" | gen-ai generate -m veo-3.1 -d 8 -s
# Fully scripted: silent, no prompts, JSON output
gen-ai generate -m flux-2-pro -p "a cat in a hat" --script | jq '.results[0].url'-s / --script = --silent --quiet --json.
| Flag | Alias | Meaning |
|---|---|---|
--model |
-m |
Model id (e.g. flux-2-pro) |
--prompt |
-p |
Text prompt (or pipe via stdin) |
--image |
-i |
Input image(s) — local path or URL, repeatable |
--video |
--vd |
Input video — local path or URL |
--aspect-ratio |
--ar |
e.g. 16:9, 9:16, 1:1
|
--resolution |
-r |
e.g. 720p, 1080p, 4k
|
--duration |
-d |
Video length in seconds |
--count |
-n |
Number of outputs |
--download <dir> |
Download directory (default ./output) |
|
--no-download |
Print the URL only | |
--save-to-drive |
--drive |
Save the result to Picsart Drive |
--dry-run |
Show the resolved payload without generating | |
--json |
Machine-readable output |
gen-ai models # browse all models with badges & pricing
gen-ai models --mode video # filter by mode
gen-ai models --provider google # filter by provider
gen-ai models info seedance-2.0 # full capabilities + parameters
gen-ai models compare kling-v3 veo-3.1
gen-ai pricing seedance-2.0 -d 5 -r 1080p # quote a cost before generating- Generating media — inputs, outputs, and modes in depth
- Files & Drive — upload, download, organize
- Batch & Automation — manifests and bulk runs
- Model Reference — per-provider model pages with CLI examples
Picsart CLI & MCP · Repo · AI Playground app
Getting Started
Interfaces
Concepts
Model Reference
Providers
- All providers
- Async
- ByteDance
- Creatify
- ElevenLabs
- Flux (Black Forest Labs)
- Grok (xAI)
- Happy Horse
- HeyGen
- Hunyuan
- Ideogram
- Kling
- LTX (Lightricks)
- Luma
- MiniMax
- OpenAI
- OVI
- Picsart
- Pika
- PixVerse
- Qwen (Alibaba)
- Recraft
- Reve
- Runway
- Seedance
- Seedream
- Topaz
- VEED
- Videography
- Wan (Alibaba)
More