ga-it

Results 15 comments of ga-it

I think the beta launch of Photoshop generative fill has amplified the opportunity for use of AI in darktable (even if via user API credentials to a cloud setvice: https://www.adobe.com/za/products/photoshop/generative-fill.html...

Hi @mudler I appreciate all your great work and workload Any word on the above? Is it my misconfiguration or is this a bone fide bug? I am stuck without...

Same issue here with exporting and the "Total Grid Import" value. When mode was "Zero Export" then sum value was correct and included non-essentials and reflected correctly on sunsynk.net. After...

Rather than work specifically with ollama, could you allow defining the endpoint for the OpenAI connection? In addition to the endpoint, this should also then allow selection of the specific...

Apologies - to clarify I was suggesting an alternative approach to @mlverse for the enhancement

Hello. First off, I just want to say that the groupfolders app is fantastic, and it’s been an essential part of our workflow. I wanted to ask if there are...

Speaker Diarization is a winner We currently use this github packaging of the whisperx project into a api server: https://github.com/richginsberg/whisperX-api @fedirz Could this be incorporated into Speaches?

Thanks for a great app @ElishaKay !!

I think OpenWebUI gets the hierarchy right. 1. User access: ![Image](https://github.com/user-attachments/assets/e47cb9f1-6cfe-4918-8fa7-7b34e188b32f) 2. Ldap integration: ![Image](https://github.com/user-attachments/assets/18a56e8b-41f6-4d54-9850-4bfc32262844) 3. Group definition: ![Image](https://github.com/user-attachments/assets/d6550b34-4af3-4d2c-a168-e778b3150dab) 4. System-wide connections: ![Image](https://github.com/user-attachments/assets/5ac76555-2ffe-47bd-a7d0-503f8191d792) 5. User connections: ![Image](https://github.com/user-attachments/assets/df6dc394-e94d-4ce7-a2a4-3ea5659ae0ad) 6. Systemwide models:...

I think this functionality would also be amazingly useful for tools and functions. For example, we have a tool that performs OCR with output as a markdown, html or json...