Ciara Rowles
ciararowles.bsky.social
Ciara Rowles
@ciararowles.bsky.social
Machine Learning Researcher | Ex - Unity | IP-Adapter-Instruct | TemporalNet | svd-controlnet | Saga of the Void | She/her | AI | VR | Game Dev | All views my own
Nano banana pro is insane, nothing is even close, the in context capabilities are bar none.
November 20, 2025 at 5:15 PM
uhhh
November 18, 2025 at 1:18 PM
Steam-oyua
November 12, 2025 at 6:02 PM
My experience today #o3pro
June 11, 2025 at 9:39 PM
I love how people are all like "more money should be spent on game development and the people making them should be paid more", then freak out when the cost of games roughly tracks inflation, despite the scope of games increasing over time, where did you think the money was going to come from?
June 8, 2025 at 10:09 PM
I'm shocked how much i like openAIs o3, the improvement is near gpt-3 -> gpt-4 for me, it's better at everything, coding with it is much less clunky and the web search is well integrated to the point where it feels natural.
April 25, 2025 at 4:57 PM
why does tagging anything with florence2 always create a perfect list of people, faces, occasional objects and always, always ... shoes?
Like 50% of the output tags are always shoes or feet for some reason.
March 22, 2025 at 9:39 PM
Reposted by Ciara Rowles
Thrilled to share that Geometry Image Diffusion has been accepted to #ICLR2025! 🚀

Paper: openreview.net/forum?id=Glm...
January 23, 2025 at 9:14 PM
Have you ever wanted to use a version of stable diffusion that had recursive cross attention layers so you could use multiple prompts in a way that didn't actually improve prompt understanding. No? Well here you go anyway:

github.com/CiaraStrawbe...
January 3, 2025 at 7:14 PM
Genuinely in love with the steam deck as a platform, got one for travelling a few months ago, but i do a large fraction of my gaming on it now, it's like the difference between the vive headset and the quest, it's just so much less effort to do anything.
December 28, 2024 at 12:20 AM
Reposted by Ciara Rowles
Does 3D generation always have to be either slow or complex and data-hungry?🤔 We don’t think so! With Geometry Image Diffusion, we’re all about reusing (and recycling ♻️) what already works — making it faster and easier by reducing complexity and data needs 🚀(1/10)
December 6, 2024 at 4:25 PM
Going to have to choose between a 5090 or a single openai pro subscription for a few months at this rate.
December 5, 2024 at 6:23 PM
Introducing my new work: Stylecodes!

An open source sref implementation for sd!

Paper here: ciarastrawberry.github.io/stylecodes.g...

Code here: github.com/CiaraStrawbe...

Stylistic control using only an easily sharable 20 digit base64 code!

#stablediffusion #midjourney
November 19, 2024 at 8:14 PM
I'm gonna move to posting here from now on I think for the most part, have some interesting stuff happening soon.
November 10, 2024 at 1:26 PM