Tool · Pictures, Video

Draw Things

A free app for iPhone, iPad and Mac that makes pictures on your own device, offline, using downloadable open models. Can also turn images into short clips and train small style add-ons (LoRAs). Optional cloud speed-up.

Go to Draw Things’s website

At a glance

Can I sell what I make?: The terms don't say clearly
No terms of service found; the privacy policy says nothing about outputs. Rights also depend on the licence of the model you download.
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review
Cost: Free option: Free Edition runs everything on your device; a free Community account adds limited Cloud Compute and Lab Hours.
Plans below.
How you use it: Phone app, Desktop app, On your own computer
iPhone, iPad and Mac. Model list page (wiki) blocked fetching; Qwen Image RAM figures from the maker's release post. FLUX.1 [dev] and SD 3.5 model cards list Draw Things as a local app.
source · checked 12 Oct 2026 · checked on the maker's own page
Skill needed: Some setup
Inferred: install app and download models; settings are detailed.
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review
Made by: Draw Things, Inc.
Country not stated on the site or privacy policy.
source · checked 12 Oct 2026 · checked on the maker's own page
Status: Available
source · checked 12 Oct 2026 · checked on the maker's own page

What you can make with it

A picture, from a description (main use)
A picture, by changing a photo I have
A picture, the same character or style across many images
A video, by bringing a photo to life

text to imageimage to imageimage to video

Site lists local generation, Infinite Canvas (expand/fill), image-to-video and on-device LoRA training. Consistent character mapped from LoRA training.

source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Plans and prices

Plan	Price	Includes
Draw Things+	$8.99 a month	Higher Cloud Compute limits, custom LoRA uploads, enhanced privacy.

Only '$' shown; USD assumed. Billing frequency assumed monthly from '/month'.

source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Rights and safety

Trains on your work?: The terms don't say clearly
Policy says creations are mostly stored on device and covers uploaded LoRA files; no mention of training.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Models it uses

Qwen-Image, FLUX.1 [dev], Stable Diffusion 3.5

Models it uses (not yet listed on Plainly)

FLUX.2 [klein] 4B

Other options for “A picture, from a description”

Adobe Express, Adobe Firefly, Adobe Photoshop, Akool, Artbreeder, Bria, Canva AI (Magic Studio), ChatGPT Images, Civitai, Clipdrop, ComfyUI, Creatify, DeeVid AI, DiffusionBee, DomoAI, Dreamina, Dzine, fal, Filmora, FlexClip, FLUX.1 [dev], FLUX.1 [schnell], FLUX.1 Kontext, FLUX.2

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.