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.
@testingcatalog
-
Comparing generative AI image models
By
–
Yeah, the perfection is not there yet. I am wondering to compare it with Leonardo Phoenix now
-
Observations on custom GPT performance post-GPT-4o release
By
–
I see. It might be the case that this was now released to custom GPTs as well. Cuz after 4o release Custom GPTs remained to perform the same
-
Observations on custom GPT output variations
By
–
It might be that now it got expanded to custom GPTs, cuz the output was very different before
-
Analysis of DALL-E system prompt configuration
By
–
Yep, it is claiming to be dalle in the system prompt as well, no change over there
-
User observation: DALL-E shows improved text rendering and stylistic variety
By
–
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
–
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
–
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!
