* start refactoring -not yet functional
* first phase of refactor done - not sure weighted prompts working
* Second phase of refactoring. Everything mostly working.
* The refactoring has moved all the hard-core inference work into
ldm.dream.generator.*, where there are submodules for txt2img and
img2img. inpaint will go in there as well.
* Some additional refactoring will be done soon, but relatively
minor work.
* fix -save_orig flag to actually work
* add @neonsecret attention.py memory optimization
* remove unneeded imports
* move token logging into conditioning.py
* add placeholder version of inpaint; porting in progress
* fix crash in img2img
* inpainting working; not tested on variations
* fix crashes in img2img
* ported attention.py memory optimization #117 from basujindal branch
* added @torch_no_grad() decorators to img2img, txt2img, inpaint closures
* Final commit prior to PR against development
* fixup crash when generating intermediate images in web UI
* rename ldm.simplet2i to ldm.generate
* add backward-compatibility simplet2i shell with deprecation warning
* add back in mps exception, addresses @vargol comment in #354
* replaced Conditioning class with exported functions
* fix wrong type of with_variations attribute during intialization
* changed "image_iterator()" to "get_make_image()"
* raise NotImplementedError for calling get_make_image() in parent class
* Update ldm/generate.py
better error message
Co-authored-by: Kevin Gibbons <bakkot@gmail.com>
* minor stylistic fixes and assertion checks from code review
* moved get_noise() method into img2img class
* break get_noise() into two methods, one for txt2img and the other for img2img
* inpainting works on non-square images now
* make get_noise() an abstract method in base class
* much improved inpainting
Co-authored-by: Kevin Gibbons <bakkot@gmail.com>
By supplying --model (defaulting to stable-diffusion-1.4) a user can specify which model to load.
Width/Height/Config Location/Weights Location are referenced from configs/models.yaml
* This functionality is triggered by the --fit option in the CLI (default
false), and by the "fit" checkbox in the WebGUI (default True)
* In addition, this commit contains a number of whitespace changes to
make the code more readable, as well as an attempt to unify the visual
appearance of info and warning messages.
* Allow configuration of which SD model to use
Closes https://github.com/lstein/stable-diffusion/issues/49 The syntax isn't quite the same (opting for --weights over --model), although --weights is more in-line with the existing naming convention.
This method also locks us into models in the models/ldm/stable-diffusion-v1/ directory. Personally, I'm not averse to this, although a secondary solution may be necessary if we wish to supply weights from an external directory.
* Fix typo
* Allow either filename OR filepath input for arg
This approach allows both
--weights SD13
--weights C:/StableDiffusion/models/ldm/stable-diffusion-v1/SD13.ckpt
Fixed merging embeddings based on the changes made in textual inversion. Tested and working. Inverted their logic to prioritize Stable Diffusion implementation over alternatives, but left the option for alternatives to still be used.
This adds an option -t argument that will print out color-coded tokenization, SD has a maximum of 77 tokens, it silently discards tokens over the limit if your prompt is too long.
By using -t you can see how your prompt is being tokenized which helps prompt crafting.
