Oh nice! I didn't know controlnet for LCM had landed.
@fofrai
-
OpenAI Text-to-Speech API: Weird Experiments Thread
By
–
OpenAI text2speech API.
— fofr (@fofrAI) 7 novembre 2023
A thread of weird experiments 🧵
Based. pic.twitter.com/yseNPDeSiXOpenAI text2speech API. A thread of weird experiments Based.
-
Combining AI Voices, Images, and Video Generation with Lip Sync
By
–
– OpenAI voices
– Midjourney image
– Runway Gen2 image to video
– VideoReTalking for lip sync https://
replicate.com/cjwbw/video-re
talking
… -
VideoReTalking AI Model Now Available on Replicate Platform
By
–
ReTalking model on Replicate https://
replicate.com/cjwbw/video-re
talking
… -
OpenAI Text-to-Speech Voices Layered for Borg Lip-Sync
By
–
Decided to get all the OpenAI text-to-speech voices to say the same thing and then layer them all back over each other.
— fofr (@fofrAI) 7 novembre 2023
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/Rl3ih3uDQADecided 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.
-
Handling Large JSON Files Within Token Limits
By
–
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.
-
AI Image Generation Prompt Flagged During Reuse Test
By
–
I passed back one of the prompts used to generate a prior image and it also got flagged.
-
DALL-E 3 Image Styles: Natural vs Vivid Quality Comparison
By
–
In dalle3, the real people live in the natural style. 1. vivid hd
2. vivid standard
3. natural hd
4. natural standard -
DALL-E 3 Settings Comparison: Vivid vs Natural Modes
By
–
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 -
Image Generation Style Parameters: Vivid vs Natural
By
–
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