On Friday, August 12, 2022 05:08:00 AM lina wrote: > I want to make a small booklet about my baby with few cartoon pictures, > like dance octopus, a cut baby, ect. > > Is there any software I can use to have the picture as they draw in a > children's book?
Hmm, I don't remember the name, but within the last 3 to 6 months I saw a "blurb" about a software package that uses AI (of some sort) to create graphics from verbal descriptions of what the user wanted. Initially it was available on a very limited basis (like maybe to selected users on an experimental basis), but I (vaguely) remember something about that software now being made available to maybe something like upto 1 million users, and there was a list to sign up for access -- I believe there was a waiting list. The sample graphics that I saw I will say looked "cartoonish" -- they were not like photorealistic images of real things. Perhaps someone else here remembers that package or maybe a google search on something like [AI image "verbal description"] might turn something up. Ahh, ok, I tried a search -- the software is named Dall-E (first name Salvador?), and here is some text from the google search: <quote> Picture This: Images Created Using Natural Language Processing enterrasolutions.com › blog › picture-this-images-created-using-natural-lan... Jan 12, 2021 · ... mere verbal description.”[2] A new program introduced by OpenAI, called DALL·E, takes the adage to heart and creates images from words. [PDF] From Visual Input to Verbal Output in the Visual Translator - CiteSeerX citeseerx.ist.psu.edu › viewdoc › download images, constitutes the central goal of computer vision. With respect to a natural language access to visual data, however, the verbal description of ... Generating Art from Neural Networks - WorldQuant www.worldquant.com › ideas › generating-art-from-neural-networks Dec 16, 2019 · What if we have no input image to start with, but only a verbal description? Let's say we have the words “a blue bird sitting on a tree ... </quote> Maybe it will be helpful. -- rhk If you reply: snip, snip, and snip again; leave attributions; avoid HTML; avoid top posting; and keep it "on list". (Oxford comma included at no charge.) If you change topics, change the Subject: line. Writing is often meant for others to read (legal agreements excepted?) -- make it easier for your reader by various means, including liberal use of whitespace. If someone else has already responded to a question, decide whether any response you add will be helpful or not ... A picture is worth a thousand words -- divide by 10 for each minute of video (or audio) or create a transcript and edit it to 10% of the original.
