aifunhouse Profile picture
Oct 1, 2022 15 tweets 8 min read Read on X
1. Last week @openai finally removed the waitlist for DALL-E!

Of the AI image creation tools out there, DALL-E is arguably the most accessible.

Today's thread provides a hands-on tutorial for new DALL-E users looking to generate visually consistent assets.

Sticker Time!
2. If you've never used DALL-E, head on over and sign up now!

First announced in April, DALL-E is the OG text-to-image ML model. For months, access was extremely limited, but now everyone, including you, can log in and take this dream machine for a spin.

labs.openai.com
3. If you need inspiration, OpenAI's Instagram is filled with images that a mere 6 month ago would have knocked our collective socks off.

Since then of course, we've all become jaded as new mind-bending tech comes out weekly.

Ah to be young again.

instagram.com/openaidalle/?h…
4. When you sign up, you'll get 50 free credits plus an additional 15 free credits each month.

Once you blow through those making photos of "well-dressed capybara prepping for a tea party", you can spend $15 for 115 more credits.

At $0.13 an image, you'll want to get serious.
5. DALL-E is great for one-off whimsy, but often you'll want multiple visual assets in a consistent visual style.

For full images, you do this by describing a subject, then adding stylistic modifiers like "oil painting by Edvard Munch"

Just look at those adorably piercing eyes.
6. What if instead of full images, you want to create something more like a graphics pack (e.g. icons or stickers)?

In this case it's useful to tell DALL-E to generate multiple items at once. This will ensure that they all share a very coherent look.
7. With the prompt:

"Four trendy hand illustrated animal stickers: a pig, a duck, a cow and a sheep, vector art"

DALL-E creates four complimentary stickers despite being given minimal stylistic guidance.

If you want a different look, you can modify the prompt as needed.
8. Once you show your friends these tasty stickers, they'll no doubt be hungry for more.

This is where inpainting comes in.

If you create a fresh batch of stickers, they won't match the current batch well. Instead click "edit", erase the sheep, then create a new animal.
Once you delete the sheep *and* the surrounding background, change the prompt to something like:

"A trendy hand illustrated stickers of farm animals and a koala, vector art"

This puts emphasis on creating a koala while still allowing the resulting image to match the prompt.
10. Inpainting with DALL-E's edit tool is also a very useful way of touching up imperfections in an image.

If you like an image, but wish a specific portion was a bit different (here our koala's left ear), you can delete it and have DALL-E generate 3 new copies to choose from.
11. Finally, here's a time saving tip if you're using this trick repeatedly to create a large number of stickers.

Instead of using edit mode, you can pre-erase the region you plan to inpaint in a photo editor.

This creates a template you can reuse with DALL-E's upload feature.
12. Now try using the template.

Click "upload an image" on DALL-E's homepage. Once you upload it, click "crop" then "edit image". You'll be able to create new stickers by entering new prompts.

TIP: To get the prompt input to appear, click the pre-erased region with the eraser.
13. As a special weekend bonus, here's an additional template we created for generating somewhat odd looking comic-style icons.

We created this template purely with DALL-E, but you'll surely get even better results if make one using a stylish icon pack you find on the web.
14. One last tip!

If you want to use the stickers/icons you create, you'll want to remove the background.

One easy way to do using the newest iOS Photos app in iOS 16. Save your stickers to Photos, crop to the sticker you want, long on press it, then choose "share" to save it.
15. Follow @aifunhouse for more tutorials, explainers, explorations, and #AI fun.

If you enjoyed this thread, please like and share.

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with aifunhouse

aifunhouse Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @aifunhouse

Dec 3, 2022
🧵Autocomplete your way to a business like it's 2025

1. Yesterday, @Noapinion + @tszzi posted a thoughtful take on where AI is headed – autocomplete for everything.

Inspired by their optimism, we used ChatGPT to prompt our way to a new side hustle.

2. On Wednesday @openai released ChatGPT, an eerily competent chatbot that sent Twitter abuzz with countless screenshots and demo threads.

Since the OpenAI team seems to know a thing or two about running an online business, we figured their chatbot would too.

Low and behold👇
3. ChatGPT's response to "How do I start an online business?" was solid, but we weren't sure where to start.

In order to make the advice actionable (a word we've heard business types use) we requested a step-by-step guide instead.

Seconds later, we had a handy 5-step checklist.
Read 14 tweets
Nov 30, 2022
🧵AI-assisted image prompts

1. In the last week, both @stabilityai and @openai have released major updates to their flagship offerings.

In this thread, we use OpenAI's new #ChatGPT model to help talk us through generating prompts for StabilityAI's new #stablediffusion v2 model.
2. ChatGPT3 is a new GPT3-powered model focused on conversing with users.

As with InstructGPT3 (the current default GPT3 model), @openai leveraged Reinforcement Learning from Human Feedback (RLHF) to boost the reliability and desirability of responses.

openai.com/blog/chatgpt/
3. If you create an @openai account, you can currently test ChatGPT for free. We tried it out with the following prompt and were immediately impressed:

"I'm looking to create images of cats using a text-to-image model, similar to DALL-E. Can you suggest some prompts?"
Read 11 tweets
Nov 11, 2022
🧵Categorizing complaints to Elon with AI

1. It's a tumultuous time here in tweet town.

For the good of the community, we used language embeddings to help @elonmusk and his team get a birds eye view of the +45k complaints he recently solicited👇

2. How do you categorize +45k replies to an @elonmusk tweet?

STEP 1: Use Twitter's API to pull all 45k replies, sorted by # of likes.

STEP 2: Show GPT-3 a sampling of top replies and ask it to suggest some categories.

STEP 3: Use text embeddings to categorize all the replies.
3. To get the replies to the tweet we used tweepy, a python wrapper for calling Twitter's V2 API.

The API has 3 tiers. Only the academic tier can pull replies that are more than 7 days old and tweets more than 30 days old (one more complaint for Elon!)

kirenz.com/post/2021-12-1…
Read 11 tweets
Nov 6, 2022
🧵Automated image generation with DALL-E

1. A few days ago @OpenAI announced that #DALLE users could create images programmatically via API.

To celebrate we took a vintage shot of @eerac, circa 2012, and through in a healthy assortment of fully automated AI whimsey. ImageImageImageImage
2. Until two days ago, DALL-E users have only ever been able to generate images through @OpenAI's website, labs.openai.com

DALL-E delivers great image quality, but without being able to use it programmatically, it's cumbersome to incorporate in to automated workflows.
3. In August, @StabilityAI's open release of #stablediffusion led to an explosion in 3rd party tools built on text-to-image AI.

While @OpenAI hasn't released their network, they have introduced a way to incorporate DALL-E in to workflows and plugins.

Read 11 tweets
Nov 2, 2022
🧵Chained Prompts + Web Lookup

1. If you've used GPT-3, you likely asked it to perform a task using a single "prompt" or instruction.

GPT-3's ability to perform tasks in one shot is impressive, but tools like @dust4ai will make it far more powerful.

2. When you prompt GPT-3 to perform a task (e.g. "write a series of tweets about elephants"), it may be more reliable to perform the task in multiple steps:

1: Write a short paragraph about elephants
2: Divide the following paragraph into a series of ~250 character tweets
3. When you do this, the output from the first call to GPT-3 is inserted in to the prompt for the second call, hence the term "chained prompts".

It makes sense that multiple calls to GPT-3 can outperform a single call, but that's only half the story.

arxiv.org/abs/2110.01691
Read 11 tweets
Oct 19, 2022
1. Text-based image editing is coming in hot!

Between #DALLE, #midjourney and #stablediffusion text-to-image generation is all the rage, but what if your images are off target?

Usually you try new prompts, then use inpainting to make edits... until now.

2. This month multiple papers have come out demonstrating how language can be used to edit an image.

Equally exciting, these papers are being implemented on top of #stablediffusion since it's now openly available (Thanks @EMostaque!)

Let's review some of the ⚡️fast progress...
3. Last week, @FerranDeLaTorre and Chen Henry Wu released both a paper and code for CycleDiffusion.

CycleDiffusion allows existing text-to-image generation networks (e.g. #stablediffusion) to be used as text-guided image editors.


github.com/ChenWu98/cycle…
Read 13 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(