TuringAI

over 2 years ago

@dogedagr8 we are aware of this you can check for information in our server

0

34

almost 3 years ago

turing status update:

2

5

2

0

934

over 2 years ago

@EndurX we made an update of our situation on our server, if you need more information please reply here or go to our discord server

0

39

Who to follow

19yo head of vibecoding @withdelphi | prev swe @get_wildfire & founder @Turing_AI_ (acq, 768k users) 🇪🇸/🇧🇷 42

Seth Juarez

@sethjuarez

I work in AI/ML @Microsoft / @GitHub. I like machine learning. Oh and the hot Mexican tamarind candy. Don't judge. Married to the beautiful @rivajuarez.

Yariv gilat

@yariv_gilat

almost 3 years ago

We are giving away 25x Nitro BOOSTS for FREE at https://t.co/GGmWFzXSGG 🎉🎉

1

0

2K

over 2 years ago

@DrunkSouzan hello,m ceo speaking here, please open a ticket in our server and ping me and i will unban you and refund your money and i will check what happened with your previous requests

0

11

Turing_AI_ retweeted

almost 3 years ago

You can use #Llama2 from @Meta for FREE at https://t.co/GGmWFzXSGG or inviting our discord bot at https://t.co/RRtQTwMIG0 . Enjoy this new AI model and compare it the most capable LLMs

1

4

2

0

2K

almost 3 years ago

You can use #Llama2 from @Meta for FREE at https://t.co/GGmWFzXSGG or inviting our discord bot at https://t.co/RRtQTwMIG0 . Enjoy this new AI model and compare it the most capable LLMs

1

4

2

0

2K

almost 3 years ago

@mava_app @WOMBO @midjourney @discord thanks

0

29

Turing_AI_ retweeted

almost 3 years ago

turing status update:

2

5

2

0

934

almost 3 years ago

image of @MrlolDev @f1nniboy developing an update for our discord bot

0

5

1

0

368

Turing_AI_ retweeted

Xander Steenbrugge

@xsteenbrugge

almost 3 years ago

SDXL TLDR: 1. SDXL seems to vastly outperform v1.5 and v2.1 in terms of user preferences and is even (roughly) tied with @midjourney v5.1!! 2. SDXL is BIG (2.6B Unet params) --> slower + more VRAM than prev SD 3. Two CLIP txt-encoders instead of one (conditioning vectors are concatenated) resulting in better img-txt alignment 4. Slightly improved VAE 5. Much better ways of dealing with low-res training imgs (condition the model on img-size), random cropping (condition the model on crop location) and non-square imgs (condition model on aspect ratio) 6. SDXL has an optional refinement stage trained specifically on denoising small amounts of noise (when there's already lots of signal) from high quality images.

xsteenbrugge's tweet photo. SDXL TLDR:
1. SDXL seems to vastly outperform v1.5 and v2.1 in terms of user preferences and is even (roughly) tied with @midjourney v5.1!!
2. SDXL is BIG (2.6B Unet params) --> slower + more VRAM than prev SD
3. Two CLIP txt-encoders instead of one (conditioning vectors are concatenated) resulting in better img-txt alignment
4. Slightly improved VAE
5. Much better ways of dealing with low-res training imgs (condition the model on img-size), random cropping (condition the model on crop location) and non-square imgs (condition model on aspect ratio)
6. SDXL has an optional refinement stage trained specifically on denoising small amounts of noise (when there's already lots of signal) from high quality images.

2

77

13

18

26K

almost 3 years ago

@JemWritesCode love it <3

0

1

0

14

almost 3 years ago

Plugins are coming

1

3

1

0

265

Turing_AI_ retweeted

about 3 years ago

just to the ones interested, @Turing_AI_ is serving more than 200k users using @supabase @nextjs @Redisinc @tailwindcss @typescript @SellixEcommerce @discord everything at https://t.co/NAKS0kMNp8

0

6

1

0

492

about 3 years ago

0

2

0

228

about 3 years ago

Video generated with #gen2 at https://t.co/GGmWFzXSGG

2

4

2

0

426

about 3 years ago

1

2

0

261

Turing_AI_ retweeted

about 3 years ago

Do you want to try #Gen2 ? join https://t.co/R3Qoqwq7mJ and wait some hours :)

0

2

1

0

232

about 3 years ago

new creations from https://t.co/GGmWFzXSGG

0

2

1

0

213

Turing_AI_ retweeted