Search
Star
Feedback
Setup for Free
© 2026 Hedgehog Software, LLC
Twitter
GitHub
Discord
System
Light
Dark
More
Communities
Docs
About
Terms
Privacy
Dreambooth training taking very long (even for 1000 steps) [4090] - Runpod
R
Runpod
•
2y ago
•
3 replies
smoke
Dreambooth training taking very long (even for 1000 steps) [4090]
Hi there
,
I am running a Dreambooth training that uses sd
-scripts under the hood but it seems like it is taking very long on a 4090
.
I use the
save_every_n_steps
save_every_n_steps
flag so I can kinda see how long it takes for every 1000 steps
. I feel like this is taking very long or am I wrong
?
Runpod
Join
We're a community of enthusiasts, engineers, and enterprises, all sharing insights on AI, Machine Learning and GPUs!
21,202
Members
View on Discord
Resources
ModelContextProtocol
ModelContextProtocol
MCP Server
Recent Announcements
Similar Threads
Was this page helpful?
Yes
No
Similar Threads
Dreambooth training api
R
Runpod / ⚡|serverless
2y ago
New release is taking too long.
R
Runpod / ⚡|serverless
2y ago
The code for LoRA training
R
Runpod / ⚡|serverless
4mo ago
SDXL Dreambooth - can’t load model
R
Runpod / ⚡|serverless
2y ago