[bug]:

[sheeba46]

Is there an existing issue for this problem?

• I have searched the existing issues

Operating system

Windows

GPU vendor

Nvidia (CUDA)

GPU model

No response

GPU VRAM

No response

Version number

5.8.1

Browser

Chrome

Python dependencies

[2025-03-26 09:14:15,726]::[InvokeAI]::ERROR --> Error while invoking session eaba1b1f-16e4-410b-8eca-de6ddcc19a32, invocation aca43717-be36-4771-9406-9fc819e4ad2f (sdxl_compel_prompt): CUDA error: the launch timed out and was terminated
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

What happened

I tried to Invoke a new image and get the above error message.....totally lost

What you expected to happen

To have run and generated an image

How to reproduce the problem

No response

Additional context

No response

Discord username

No response

[psychedelicious]

• Please share your GPU model and how much VRAM it has
• Please try updating GPU drivers and restarting the system

[sheeba46]

NVIDIA GeForce GTX TITAN X Manufacturer NVIDIA Model GeForce GTX TITAN X Device ID 10DE-17C2 Revision A2 Subvendor NVIDIA (10DE) Current Performance Level Level 0 Current GPU Clock 135 MHz Current Memory Clock 405 MHz Current Shader Clock 405 MHz Voltage 0.837 V Technology 28 nm Bus Interface PCI Express x16 Temperature 51 °C Driver version 32.0.15.6094 BIOS Version 84.00.45.00.03 Memory 4095 MB Count of performance levels : 3 Level 1 - "Perf Level 0" GPU Clock 1001 MHz Shader Clock 3505 MHz Level 2 - "Base" GPU Clock 1002 MHz Shader Clock 3505 MHz Level 3 - "Boost" GPU Clock 1076 MHz Shader Clock 3505 MHz GPU details above. Yes I have already updated and restarted several times. Thanks for responding Bill B

…

On Wed, 26 Mar 2025 at 13:53, psychedelicious ***@***.***> wrote: - Please share your GPU model and how much VRAM it has - Please try updating GPU drivers and restarting the system — Reply to this email directly, view it on GitHub <#7839 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AIDKCT6OWUBOBYD55FXJMOT2WIJCZAVCNFSM6AAAAABZYZPA66VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDONJTGEYTENRXGM> . You are receiving this because you authored the thread.Message ID: ***@***.***> [image: psychedelicious]*psychedelicious* left a comment (invoke-ai/InvokeAI#7839) <#7839 (comment)> - Please share your GPU model and how much VRAM it has - Please try updating GPU drivers and restarting the system — Reply to this email directly, view it on GitHub <#7839 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AIDKCT6OWUBOBYD55FXJMOT2WIJCZAVCNFSM6AAAAABZYZPA66VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDONJTGEYTENRXGM> . You are receiving this because you authored the thread.Message ID: ***@***.***>

[sheeba46]

Additional info from Task Manager Cheers Bill G

…

On Wed, 26 Mar 2025 at 15:44, Bill Gregory ***@***.***> wrote: NVIDIA GeForce GTX TITAN X Manufacturer NVIDIA Model GeForce GTX TITAN X Device ID 10DE-17C2 Revision A2 Subvendor NVIDIA (10DE) Current Performance Level Level 0 Current GPU Clock 135 MHz Current Memory Clock 405 MHz Current Shader Clock 405 MHz Voltage 0.837 V Technology 28 nm Bus Interface PCI Express x16 Temperature 51 °C Driver version 32.0.15.6094 BIOS Version 84.00.45.00.03 Memory 4095 MB Count of performance levels : 3 Level 1 - "Perf Level 0" GPU Clock 1001 MHz Shader Clock 3505 MHz Level 2 - "Base" GPU Clock 1002 MHz Shader Clock 3505 MHz Level 3 - "Boost" GPU Clock 1076 MHz Shader Clock 3505 MHz GPU details above. Yes I have already updated and restarted several times. Thanks for responding Bill B On Wed, 26 Mar 2025 at 13:53, psychedelicious ***@***.***> wrote: > > - Please share your GPU model and how much VRAM it has > - Please try updating GPU drivers and restarting the system > > — > Reply to this email directly, view it on GitHub > <#7839 (comment)>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AIDKCT6OWUBOBYD55FXJMOT2WIJCZAVCNFSM6AAAAABZYZPA66VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDONJTGEYTENRXGM> > . > You are receiving this because you authored the thread.Message ID: > ***@***.***> > [image: psychedelicious]*psychedelicious* left a comment > (invoke-ai/InvokeAI#7839) > <#7839 (comment)> > > - Please share your GPU model and how much VRAM it has > - Please try updating GPU drivers and restarting the system > > — > Reply to this email directly, view it on GitHub > <#7839 (comment)>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AIDKCT6OWUBOBYD55FXJMOT2WIJCZAVCNFSM6AAAAABZYZPA66VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDONJTGEYTENRXGM> > . > You are receiving this because you authored the thread.Message ID: > ***@***.***> >

[psychedelicious]

Hmm not sure what the problem is, but I'm not familiar with that GPU. Did it ever work in Invoke? How about other AI image gen apps? Did you try an SD1.5 model?