I've added all of these: https://
github.com/fofr/cog-comfy
ui/commit/56532c94fb5f0ac2587ba4822b4e55af93a15347
… UltimateSDupscaler should have been a given
@fofrai
-
UltimateSDupscaler Added to Comfy UI Integration
By
–
-
Weight-free AI model startup performance issue
By
–
Not sure what's happened there. It's a weight-free model so start up is fast. If you DM me the details I'll raise with team.
-
Midjourney v3 Output Discovered in v6 Release
By
–
I found a Midjourney v3 output in v6, instant favourite.
-
Native 2048x Fast Model Development Without Upscaling
By
–
I’m hoping for a native 2048x fast model, not an upscaler.
-
First Look at Stable Diffusion 3 Model Release
By
–
Is this our first look at Stable Diffusion 3? Emad hinted at this in July last year. My guess is that this is a new model not an SDXL iteration. Also quoting again because I like the new cat picture better.
-
Mona Lisa Family Generated with AI Image Generation
By
–
Mona and the Lisa family outing. 4 people generated from the features of the Mona Lisa painting.
-
PhotoMaker generates creative group selfies from single person input
By
–
Wow, you can give PhotoMaker 1 person and ask for many people, and get weird interesting results. "A photo of 4 people taking a selfie img" Group selfie of Isaac Newton, like a weird imaginary family photo. These siblings were close. Replicate prediction link below.
-
Congratulations on Creating New Art Forms with AI
By
–
Wow! Congratulations. Much deserved. You're carving new art forms.
-
Replicate Model Upload Best Practices Guide
By
–
If you upload models to Replicate, I've put together a short best practices guide to make the model the best it can be: https://
replicate.com/guides/model-b
est-practices
… Let me know if there's anything missing. -
PhotoMaker Multi-Person Generation Experiments and Results
By
–
Has anyone experimented with putting different people into a single PhotoMaker gen? I tried the Oscars selfie as an input. It's weird.