MULTIMODAL AI

Keeping up with the pace of new AI model releases

By

–

13 June 2024 14h42

Me, trying to keep up with all the AI news and test all the newly released models 🤖

Feels like it e/acced too much already.

* GPT-4o + Luma Labs pic.twitter.com/sjoib45Aak
— 🚨 AI News | TestingCatalog (@testingcatalog) 13 juin 2024

Me, trying to keep up with all the AI news and test all the newly released models Feels like it e/acced too much already. * GPT-4o + Luma Labs

Technical discussion on GPT-4o native multimodal image generation

By

–

13 June 2024 13h46

What has been expected so far is a possibility for 4o to generate images with multimodality and not by talking to DALL-E model as it user to be before. Cuz earlier, 4o was generating a prompt and was passing it to DALL-E

Speculation on upcoming multimodal AI model responses

By

–

13 June 2024 12h45

I also have a feeling that there might be a response coming to SD3 and Leonardo Phoenix. I would guess it can be 4o multimodal.

User preference between DALL-E and Phoenix AI models

By

–

13 June 2024 12h32

Phoenix output. DALL-E wins imo

User observation: DALL-E shows improved text rendering and stylistic variety

By

–

13 June 2024 11h16

BREAKING: Something is happening with DALL-E on ChatGPT Now it is performing much better at drawing text and seems to be using a bit different styles in comparison to what has been used before. Did anyone observe the same?

Discussion on GPT-4o Multimodal Image Generation Capabilities

By

–

13 June 2024 11h16

I remember that 4o was meant to become multimodal so it can be used to generate images directly without a need to use DALL-E underneath. It is happening? First noticed on the Cyberpunk Artist GPT

Luma Labs AI updates video interface with grid view and queue status

By

–

13 June 2024 10h59

Looks like @LumaLabsAI also did a small UI update. Now your videos are shown in a grid of 2 rows and you can also see the queue status in a bit better way Looks much better now!

User experience with Luma Dream Machine’s image-to-video capabilities

By

–

13 June 2024 10h59

Got all my Dream Machine creations ready in the morning 👀

1 out of 4 was good and this one was based on the image and not a plain text prompt.

It is indeed the most advanced model so far b/c it is not only generating a motion but an actual scene 🎬

It follows instructions… https://t.co/ysgbLy3cZU pic.twitter.com/N3XWgA2pkM
— 🚨 AI News | TestingCatalog (@testingcatalog) 13 juin 2024

Got all my Dream Machine creations ready in the morning 1 out of 4 was good and this one was based on the image and not a plain text prompt. It is indeed the most advanced model so far b/c it is not only generating a motion but an actual scene It follows instructions