unsupported dtype 'F64' about stable-diffusion.cpp HOT 10 OPEN

Alright here it is, feel free to give it a try. I was able to use it to convert both I64 and F64 containing models to something sdcpp could work with:

https://github.com/grauho/sdc

from stable-diffusion.cpp.

I've written a small converter program in C that re-encodes entire safetensor files that does seem to do the job, once I put in handling for those using big-endian systems I'll publish it. Having trouble getting similar logic to work a la carte at tensor loading time in sdcpp though.

from stable-diffusion.cpp.

https://civitai.com/models/8124?modelVersionId=87886
https://civitai.com/models/7371/rev-animated

Look for the bigger files, like 4-5GB. they often are FP64

from stable-diffusion.cpp.

Can you manually set the type to f32?

from stable-diffusion.cpp.

I have the same issue with a model called revAnimated_v122 but trying to convert it to F32 or F16 it gets corrupt and takes only 809Kb

Did you managed to fix it?

from stable-diffusion.cpp.

Having this issue too with other models in the SD1.5 family.

Could this be looked at?

from stable-diffusion.cpp.

I suspect this has to do with GGML currently only having support for up to 32-bit width integer and float types in it's ggml_type. It might be possible if one is willing to accept a loss in precision to convert down to a 32-bit float, provided it does not exceed FLT_MAX, via a callback in the sdcpp load_tensors function.

from stable-diffusion.cpp.

Could someone please link a model where they are having the F64 problem? I think I've put together a fix that at least seems to work with the LoRAs I have that use I64.

from stable-diffusion.cpp.

https://github.com/grauho/sdc

can you add converting to fp16 too?

from stable-diffusion.cpp.

https://github.com/grauho/sdc

can you add converting to fp16 too?

It now has handling to convert down into F16 as well as BF16 using the -f, --float-out switch, although with the caveat that if your system isn't using IEEE format floats and doubles it might not get the conversion right. Don't use the --replace option unless you want to risk losing data.

from stable-diffusion.cpp.