Commit Graph

162 Commits

Author SHA1 Message Date
Lincoln Stein
a01b7bdc40 add web interface for seamless option 2022-09-03 13:43:04 -04:00
Lincoln Stein
6566c2298c add scalable support for new models using a configs/models.yaml file 2022-09-03 11:45:21 -04:00
Lincoln Stein
063b4a1995 add ability to specify location of config file (models.yaml) 2022-09-03 11:36:04 -04:00
Lincoln Stein
91cce6b4c3 move special-casing test for precision on mps into T2I class 2022-09-03 09:43:18 -04:00
prixt
a61e49bc97 * Removed unnecessary code
* Added description about --seamless
2022-09-03 22:39:35 +09:00
Lincoln Stein
f46916d521 Add warning message about change in default host 2022-09-03 09:33:02 -04:00
Lincoln Stein
12755c6ef6 Merge branch 'web-host-port' of github.com:cgodley/stable-diffusion into cgodley-web-host-port
this allows host and port to be set on --web command line.
changes default binding from 0.0.0.0 to 127.0.0.1
2022-09-03 09:12:32 -04:00
Kevin Gibbons
e918cb1a8a replace list delimiters in variations syntax 2022-09-02 23:51:22 -07:00
prixt
d922b53c26 added seamless tiling mode and commands 2022-09-03 15:13:31 +09:00
Cragin Godley
2288412ef2
dream.py: fix indentation 2022-09-02 15:00:07 -04:00
Cragin Godley
6bff985496
dream.py: include 0.0.0.0 in --host help
Co-authored-by: Kevin Gibbons <bakkot@gmail.com>
2022-09-02 14:58:57 -04:00
Cragin Godley
918ade12ed
dream.py: use localhost in url when host is 0.0.0.0
Co-authored-by: Kevin Gibbons <bakkot@gmail.com>
2022-09-02 14:56:52 -04:00
Cragin Godley
68f62c8352 web: allow custom host/port, default to 127.0.0.1 for security reasons 2022-09-02 12:27:12 -04:00
Kevin Gibbons
4fe265735a support generating variations
Co-authored-by: xra <mail@xra.dev>
2022-09-01 23:48:53 -07:00
Lincoln Stein
629ca09fda Merge branch 'dream-m1' of github.com:toffaletti/stable-diffusion into toffaletti-dream-m1
* Fix conflicts with main branch changes
* Fix logic error in choose_autocast_device() that was causing crashes
on CUDA systems.
2022-09-01 17:54:01 -04:00
David Wager
68eabab2af
Deprecate --laion400m and --weights arguments
Removes functionality for the --laion400m and --weights arguments and notifies user to use the --model argument instead.
2022-09-01 20:46:53 +01:00
David Wager
7db51d0171
Merge branch 'main' into main 2022-09-01 19:27:38 +01:00
Lincoln Stein
1b3c7acce3 fix ambiguous naming of self.device 2022-09-01 14:18:17 -04:00
Lincoln Stein
e6b2c15fc5 Merge branch 'main' into fit-init-img
add a --fit option to limit the size of the initial image to the
maximum boundaries specified by width and height.
2022-09-01 14:09:46 -04:00
David Wager
d319b8a762
Reference model from configs/models.yaml
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
2022-09-01 19:04:31 +01:00
Lincoln Stein
01e05a98de this fixes the inconsistent use of self.device, sometimes a str and sometimes an obj 2022-09-01 10:16:05 -04:00
Lincoln Stein
c5e95adb49 closes #273, crash on M1 machines 2022-09-01 10:01:41 -04:00
Lincoln Stein
dc30adfbb4 closes #273, crash on M1 machines 2022-09-01 01:09:56 -04:00
Jason Toffaletti
66fe110148 default full_prevision to True for mps device 2022-08-31 22:03:50 -07:00
James Reynolds
70119602a0
Issue 270 fix (#274)
* check if torch.backends has mps before calling it

* Fixes issue 270

Co-authored-by: James Reynolds <magnsuviri@me.com>
2022-09-01 00:59:20 -04:00
Lincoln Stein
28fe84177e optionally scale initial image to fit box defined by width x height
* 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.
2022-09-01 00:52:43 -04:00
David Wager
ed513397b2
Allow configuration of which SD model to use (#263)
* 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
2022-08-31 14:20:28 -04:00
David Ford
58e3562652
Fix merging embeddings (#226)
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.
2022-08-31 11:24:11 -04:00
Kevin Gibbons
d566ee092a move make_grid into image_utils 2022-08-30 22:03:53 -07:00
Kevin Gibbons
153c93bdd4 refactor pngwriter 2022-08-30 22:03:51 -07:00
Lincoln Stein
bdb0651eb2 add support for Apple hardware using MPS acceleration 2022-08-31 00:33:23 -04:00
Kevin Gibbons
1714816fe2
remove support for batch_size from dream.py (#227)
* remove dream.py support for batch_size

* expect to get a single image
2022-08-30 22:30:12 -04:00
Lincoln Stein
42ffcd7204 add the recently added commands to the readline command-line-completion list; fix command-line documentation bug, closing issue #188 2022-08-29 22:34:09 -04:00
Lincoln Stein
d48299e56c Merge branch 'prompt_as_dir' of https://github.com/BlueAmulet/stable-diffusion into BlueAmulet-prompt_as_dir 2022-08-29 22:13:37 -04:00
BlueAmulet
2e22d9ecf1 Address bakkot review 2022-08-29 18:10:15 -06:00
BlueAmulet
4f8e7356b3 Add prompt as output directory feature
Based on previous code by czyz
2022-08-29 14:52:02 -06:00
Lincoln Stein
7fe7cdc8c9
Merge pull request #176 from xraxra/show-tokenization
Print out tokenization data during image generation, allowing truncated prompts to be visible.
2022-08-29 15:36:10 -04:00
Lincoln Stein
63178c6a8c
Merge branch 'main' into patch-1 2022-08-29 15:12:14 -04:00
Lincoln Stein
38701a6d7b Fix IndexError when generating grid; --grid option can now be passed on shell command line 2022-08-29 13:52:44 -04:00
Lincoln Stein
c7db038c96 grid is broken, needs the grid-fix PR#166 to fix 2022-08-29 13:39:20 -04:00
xra
fef632e0e1 tokenization logging (take 2)
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.
2022-08-29 12:28:49 +09:00
Kevin Gibbons
7ae79b350e write log files in utf-8, not ascii 2022-08-28 20:00:11 -07:00
Benjamin Warner
529040708b Fix grid image saving, log to outdir path, display sampler options once 2022-08-28 19:34:55 -05:00
Lincoln Stein
b85773f332 resolved conflicts and write properly-formatted prompt string (with sampler & upscaling) into image file 2022-08-28 19:01:45 -04:00
Lincoln Stein
8bbe7936bd close Issue #165 2022-08-28 18:21:20 -04:00
Lincoln Stein
7c485a1a4a adjusted -U upscaling argument so that it defaults to upscaling strength 0.75 if the second argument is not given 2022-08-28 17:26:39 -04:00
Lincoln Stein
ea2ee33be8 cosmetic fixup to how the outputs are reported 2022-08-28 17:06:33 -04:00
Lincoln Stein
7dfca3dcb5 moved scripts/dream_server.py into ldm/dream/server.py 2022-08-28 16:37:27 -04:00
blessedcoolant
614974a8e8
Merge branch 'main' into gfpgan-optimization 2022-08-29 08:22:26 +12:00
blessedcoolant
6e49c070bb Optimize and Improve GFPGAN and Real-ESRGAN Pipeline 2022-08-29 08:14:29 +12:00