stable-diffusion-webui-forge
stable-diffusion-webui-forge copied to clipboard
LORAs not working with flux1-dev-Q8-0.gguf
Since commit 13d6f8ed900b0857e9872e67befb02f7ed54da35 LORAs don't seem to work with the flux1-dev-Q8-0.gguf checkpoint.
Generating without a LORA seems fine, but adding one causes the error in the attached txt file.
Tried all LORAs I have and none work, all error.
Trying the same thing with flux1-dev-fp8.safetensors seems fine and does not error.
Issue does not occur when rolling back to ba01ad3
As of the latest commit, they are not working for me at all, I have the correct VAE, encoder etc it appears to work fine but at the last steps it still turns black. I have tried many quants.
Just to add this is fixed now
As of the latest commit, they are not working for me at all, I have the correct VAE, encoder etc it appears to work fine but at the last steps it still turns black. I have tried many quants.
I had this when I was using the 8 bit VAE. I switched to 16bit and it fixed it.
@blakejrobinson please could you link it to me
It's over in the black-forest HF at https://huggingface.co/black-forest-labs/FLUX.1-dev/tree/main ae.safetens
I did in fact have the smaller file, thank you
I did in fact have the smaller file, thank you
No problem - glad it fixed it. I think the smaller one worked up until a few days ago. Not sure if this is a bug, though.
Just to add this is fixed now
As of the latest commit, they are not working for me at all, I have the correct VAE, encoder etc it appears to work fine but at the last steps it still turns black. I have tried many quants.
I had this when I was using the 8 bit VAE. I switched to 16bit and it fixed it.
how or what folder do i change this file?