* Refactor generate.py and dream.py
* config file path (models.yaml) is parsed inside Generate() to simplify
API
* Better handling of keyboard interrupts in file loading mode vs
interactive
* Removed oodles of unused variables.
* move nonfunctional inpainting out of the scripts directory
* fix ugly ddim tqdm formatting
* fix embiggen breakage, formatting fixes
* fix web server handling of rel and abs outdir paths
* Can now specify either a relative or absolute path for outdir
* Outdir path does not need to be inside the stable-diffusion directory
* Closes security hole that allowed user to read any file within
stable-diffusion (eek!)
* Closes#536
* revert inadvertent change of conda env name (#528)
* Refactor generate.py and dream.py
* config file path (models.yaml) is parsed inside Generate() to simplify
API
* Better handling of keyboard interrupts in file loading mode vs
interactive
* Removed oodles of unused variables.
* move nonfunctional inpainting out of the scripts directory
* fix ugly ddim tqdm formatting
* Refactor pip requirements across the board
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
* fix name, version in setup.py
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
* Update notebooks for new requirements file changes
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
* slightly more consistent in how the different scenarios are described
* moved the stuff about `/usr/bin/python` to be adjacent to the stuff about `/usr/bin/python3`
* added an example of the 'option 1' goal state
* described a way to directly answer the question: how many snakes are living in your computer?
Code cleanup and attention.py einsum_ops update for M1 16-32GB performance.
Expected: On par with fastest ever from 8 to 128GB for 512x512. Allows large images.
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.
