@fofrai - AI Dynamics - Page 73 of 81

Decided to get all the OpenAI text-to-speech voices to say the same thing and then layer them all back over each other.

And then lip-sync it to a borg.

It's interesting that the different voices all had exactly the same duration of output for the text. pic.twitter.com/Rl3ih3uDQA
— fofr (@fofrAI) 7 novembre 2023

Decided to get all the OpenAI text-to-speech voices to say the same thing and then layer them all back over each other. And then lip-sync it to a borg. It's interesting that the different voices all had exactly the same duration of output for the text.

→ View original post on X — @fofrai

7 November 2023

Handling Large JSON Files Within Token Limits

By

@fofrai

–

07 November 2023 10h13

I tried a 12mb json file which was too many tokens, I think 200k limit. I tried a smaller json file and it needed instructions on structure to efficiently search it.

→ View original post on X — @fofrai

7 November 2023

AI Image Generation Prompt Flagged During Reuse Test

By

@fofrai

–

07 November 2023 0h36

I passed back one of the prompts used to generate a prior image and it also got flagged.

→ View original post on X — @fofrai

7 November 2023

DALL-E 3 Image Styles: Natural vs Vivid Quality Comparison

By

@fofrai

–

06 November 2023 23h55

In dalle3, the real people live in the natural style. 1. vivid hd
2. vivid standard
3. natural hd
4. natural standard

→ View original post on X — @fofrai

6 November 2023

DALL-E 3 Settings Comparison: Vivid vs Natural Modes

By

@fofrai

–

06 November 2023 23h48

I can't seem to keep prompt/seed consistent, but here's some comparisons of the 4 main dalle3 settings: 1. vivid standard
2. vivid hd
3. natural standard
4. natural hd

→ View original post on X — @fofrai

6 November 2023

Image Generation Style Parameters: Vivid vs Natural

By

@fofrai

–

06 November 2023 23h39

There's one further param listed on the endpoint docs: – style, either "vivid" or "natural"
– vivid causes the model to lean towards generating hyper-real and dramatic images
– natural causes the model to produce more natural, less hyper-real looking images

→ View original post on X — @fofrai

6 November 2023

DALL-E 3 API: Key Features and Specifications Overview

By

@fofrai

–

06 November 2023 22h59

Taking a look at the dalle3 API: – 1024×1024, 1024×1792 or 1792×1024
– 1 image per request (but can do more in parallel)
– prompts will be automatically re-written for safety, and to add more detail
– standard and HD quality, HD has more detail No seed, no negative prompts, no

→ View original post on X — @fofrai

6 November 2023