okay i terminated pod but i do have a storge hopefully it didnt delted my files or trained models
okay i terminated pod but i do have a storge hopefully it didnt delted my files or trained models
RDid you save the files in the network storage?
RIIRC, the network storage is mounted at a specific location.
Fshown in every tutorial
Fi recommend watch this one
FYouTubeSECourses
Stability AI published their most power newest model Stable Diffusion 3.5 Large. This model unlike FLUX is full model not distilled and has huge potential. I have done extensive research and publishing all of it in this video regarding how to use SD 3.5 Large with the best settings. Moreover, I am sharing how to use FLUX DEV with the best possib...
Fit was a permanent storage
Vdoc i have a question - trying to resume a kohya ss finetune. but when i load the last training state it still goes back to step 1 as if it is retraining from scratch
Fit will show as 1
Fbut will continue from last
Fso reduce number of epochs
Vah ok. thank you
Vi had a windows update kill my session overnight around 3am so if you were running this on windows it's likely the operating system started doing funky stuff and threw this off.
Xwhich video do you reccomend i watch so that i can run swarm_ui in runpod?
Vgo to his page on youtube and watch the full swarmui playlist. you have to watch the windows stuff to learn all the tidbits.
FYouTubeSECourses
In this video, I demonstrate how to install and use #SwarmUI on cloud services. If you lack a powerful GPU or wish to harness more GPU power, this video is essential. You'll learn how to install and utilize SwarmUI, one of the most powerful Generative AI interfaces, on Massed Compute, RunPod, and Kaggle (which offers free dual T4 GPU access for ...
JI'm trying wan 2.1 with FP8 and it doesn't work. I have tried everything and it still doesn't work. No torch version works, neither stable nor nightly. I even tried to install an older version of the autoinstaller with a same day commit with the same problem. I think the latest nvidia drivers have broken something. FP16 works perfectly, but it takes 1,5h to generate a video from an image.
Fi am testing fp8 it is working for me on rtx 5090 and 3090 ti. let me test again
Jwith latest nvidia drivers?
JI have a 4080
F
F572.60
Fye both 3090 ti and 5090 working
J572.70 here
Fi will update lets see
Fbut i dont think will break
Fdid you make entirely fresh install?
Jwith previous drivers was working fine. Now it doesn't work
Fok let me update maybe they truly broken
Fyou can return back to older driver easy
JI'll try to back to older drivers later
JI'm testing img to video btw, I don't know if other models has the same issue
T@Dr. Furkan Gözükara how can i know if the model i donwloaded is corrupt ?
Ti didn't use your script but manually downloaded using idm
Fit would give error while loading
Fbut best way is check their sha256
Fhugging face shows
Fjust tested WAN 2.1 14B Image-to-Video 480P even with LoRA
Fno errors
X14:36:40.846 [Error] [WebAPI] Error handling API request '/API/GenerateText2ImageWS' for user 'local': Internal exception while handling prior exception closure: System.Net.WebSockets.WebSocketException (0x80004005): The WebSocket is in an invalid state ('Aborted') for this operation. Valid states are: 'Open, CloseReceived, CloseSent'
at System.Net.WebSockets.WebSocketValidate.ThrowIfInvalidState(WebSocketState currentState, Boolean isDisposed, WebSocketState[] validStates)
at System.Net.WebSockets.ManagedWebSocket.CloseAsync(WebSocketCloseStatus closeStatus, String statusDescription, CancellationToken cancellationToken)
--- End of stack trace from previous location ---
at SwarmUI.WebAPI.API.HandleAsyncRequest(HttpContext context) in /workspace/SwarmUI/src/WebAPI/API.cs:line 165
14:38:26.237 [Info] Generated an image in 2.62 min (prep) and 67.91 sec (gen)
at System.Net.WebSockets.WebSocketValidate.ThrowIfInvalidState(WebSocketState currentState, Boolean isDisposed, WebSocketState[] validStates)
at System.Net.WebSockets.ManagedWebSocket.CloseAsync(WebSocketCloseStatus closeStatus, String statusDescription, CancellationToken cancellationToken)
--- End of stack trace from previous location ---
at SwarmUI.WebAPI.API.HandleAsyncRequest(HttpContext context) in /workspace/SwarmUI/src/WebAPI/API.cs:line 165
14:38:26.237 [Info] Generated an image in 2.62 min (prep) and 67.91 sec (gen)
Xgetting this error after trying to genrate image
Tits not corrupt
Tidk why its not working
T...
Xi know what i happened i think
Xtrying again
Xworking
X:)))
JI just rendered my first fp16 video on wan 2.1 and quality is great (far better than fp8) but last 1,5h to generate it. I need the Teacache update
Fi think generated