Firas comments

Repositories
Issues
Comments

Results 4 comments of


                                            Firas

DefaultCPUAllocator: not enough memory: you tried to allocate 22151168 bytes - llama-4bit

Same issue here, both on windows and WSL(manual anaconda).I peak at 30GB vram then the process crashes.

Training on the v.2.0 512 weights creates the wrong .yaml file

I have the same issue, trained SD2.0 512 model only for it to load in V mode, checked the .yaml and indeed it seems the 768 one was used. Weird...

Training on the v.2.0 512 weights creates the wrong .yaml file

[512test.yaml.txt](https://github.com/d8ahazard/sd_dreambooth_extension/files/10173070/512test.yaml.txt)

Training on the v.2.0 512 weights creates the wrong .yaml file

Removing parameterization: "v" from the .yaml file also makes the output become completely garbage (but not tan, just random), So it seems this 512 model only "functions" using v-mode now...