You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
First and foremost, please accept my sincere congratulations on the extraordinary work you have accomplished with the Krita AI Diffusion plugin. It has truly revolutionized the workflow for countless artists and stands as a remarkable asset to the Krita community.
I am writing to share a concept aimed at further democratizing access to the plugin. As an enthusiast in this field, I’ve observed that one of the main entry barriers for new users remains the requirement of a powerful GPU — which unfortunately excludes many talented individuals.
💡 Core Suggestion
I propose exploring the integration of an image generation option that leverages a free cloud service, specifically Google Colab. The idea is to enable users without adequate local hardware to run the AI backend through a Colab notebook and connect the Krita plugin to it. This would function similarly to the existing connectivity with the A1111 Web UI and Gradio interfaces.
✅ Anticipated Benefits
Democratization: This approach would greatly expand the number of users able to benefit from the plugin.
Gateway: It would provide an excellent entry point for newcomers, allowing them to fully experience the tool before investing in hardware.
Flexibility: Users working on laptops or low-end systems could generate images from virtually anywhere.
🚧 Foreseen Challenges and Request for Input
I understand that this is not a trivial implementation. Since the current plugin relies on the ComfyUI API, adopting an A1111-based solution would mean supporting an entirely different API, which represents a considerable development effort. In addition, addressing UX aspects of Colab — such as startup delays and connection instability — would be essential.
I’ve also noticed your integration of Interstice.cloud (which is a fantastic step forward!) — showing your commitment to cloud-based solutions. My idea is intended as a complementary, free alternative — one with inherent limitations, but one that could reach a broader audience.
I mainly wish to present this concept for your consideration and would deeply appreciate your technical and strategic insights regarding its feasibility. Perhaps there could be a pathway to run the ComfyUI backend itself on Colab in an optimized form for the plugin, elegantly avoiding the API compatibility issue.
Thank you once again for this spectacular project!
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
First and foremost, please accept my sincere congratulations on the extraordinary work you have accomplished with the Krita AI Diffusion plugin. It has truly revolutionized the workflow for countless artists and stands as a remarkable asset to the Krita community.
I am writing to share a concept aimed at further democratizing access to the plugin. As an enthusiast in this field, I’ve observed that one of the main entry barriers for new users remains the requirement of a powerful GPU — which unfortunately excludes many talented individuals.
💡 Core Suggestion
I propose exploring the integration of an image generation option that leverages a free cloud service, specifically Google Colab. The idea is to enable users without adequate local hardware to run the AI backend through a Colab notebook and connect the Krita plugin to it. This would function similarly to the existing connectivity with the A1111 Web UI and Gradio interfaces.
✅ Anticipated Benefits
Democratization: This approach would greatly expand the number of users able to benefit from the plugin.
Gateway: It would provide an excellent entry point for newcomers, allowing them to fully experience the tool before investing in hardware.
Flexibility: Users working on laptops or low-end systems could generate images from virtually anywhere.
🚧 Foreseen Challenges and Request for Input
I understand that this is not a trivial implementation. Since the current plugin relies on the ComfyUI API, adopting an A1111-based solution would mean supporting an entirely different API, which represents a considerable development effort. In addition, addressing UX aspects of Colab — such as startup delays and connection instability — would be essential.
I’ve also noticed your integration of Interstice.cloud (which is a fantastic step forward!) — showing your commitment to cloud-based solutions. My idea is intended as a complementary, free alternative — one with inherent limitations, but one that could reach a broader audience.
I mainly wish to present this concept for your consideration and would deeply appreciate your technical and strategic insights regarding its feasibility. Perhaps there could be a pathway to run the ComfyUI backend itself on Colab in an optimized form for the plugin, elegantly avoiding the API compatibility issue.
Thank you once again for this spectacular project!
Sincerely,
Zenito
Beta Was this translation helpful? Give feedback.
All reactions