John PRO

@victor
The error is back.
Have you guys Identified the problem yet?
This is becoming a problem I am finding it hard to test models if the HF Inference API fail and dont work.

If this continue you will start losing paying customers. Your attempt to milk users for money is starting to backfire.
No point in charging people for stuff that dont work. As a Pro member I have continued to support this platform with the faith that you will resolve the issues, but my patience is starting to run thin.

Please Fix the issue. I Hope that this will be done before my next billing cycle. If not. I will have no choice but cancel.

What are being done about
("ZeroGPU worker error", "GPU task aborted")
gradio.exceptions.Error: 'GPU task aborted'

This happen intermittently but often enough to annoy me.
out of 5 attempts I would get this error 3 times, sometimes after the first attempt the 2nd render would be successful,

but if not I reduce "steps" to compensate, allowing the same seed to generate,

Why did it fail?
Why would it sometimes succeed on the 2nd attempt without changing any settings,
Lora weights, steps, CFG, prompt or seed ?
Can this be fixed or can the GPU time lost because of the error be refunded?

Thank you in advance for your assistance.