Mihai 0bc6779361

Disable autocast for cpu to fix error. Remove unused precision arg. (#518) ...

When running on just cpu (intel), a call to torch.layer_norm would error with RuntimeError: expected scalar type BFloat16 but found Float
Fix buggy device handling in model.py.
Tested with scripts/dream.py --full_precision on just cpu on intel laptop. Works but slow at ~10s/it.

2022-09-12 16:55:21 -04:00

..

generator

Add Embiggen automation to upscale-cut-img2img-stitch and achieve high res without extra VRAM (#437)

2022-09-12 15:37:26 -04:00

conditioning.py

Refactoring simplet2i (#387)

2022-09-05 20:40:10 -04:00

devices.py

Disable autocast for cpu to fix error. Remove unused precision arg. (#518)

2022-09-12 16:55:21 -04:00

image_util.py

optionally scale initial image to fit box defined by width x height

2022-09-01 00:52:43 -04:00

pngwriter.py

Add Embiggen automation to upscale-cut-img2img-stitch and achieve high res without extra VRAM (#437)

2022-09-12 15:37:26 -04:00

readline.py

Refactoring simplet2i (#387)

2022-09-05 20:40:10 -04:00

server.py

fix bug which caused seed to get "stuck" on previous image even when UI specified -1

2022-09-08 23:57:45 -04:00