* Add H2OGPT
* Add UI tab for h2ogpt
* Add source files from h2ogpt
* Add the rest of the files
* Add h2ogpt support
* Add SHARK Compilation support for langchain model for cli mode
---------
Co-authored-by: George Petterson <gpetters@protonmail.com>
* Generates the seeds for all batch_count batches being run up front
rather than generating the seed for a batch just before it is run.
* Adds a --repeatable_seeds argument defaulting to False
* When repeatable_seeds=True, the first seed for a set of batches will
also be used as the rng seed for the subsequent batch seeds in the run.
The rng seed is then reset.
* When repeatable_seeds=False, batch seeding works as currently.
* Update scripts under apps/scripts that support the batch_count
argument to also support the repeatable_seeds argument.
* UI/Web: Adds a checkbox element on each SD tab after batch count/size
for toggling repeatable seeds, and update _inf functions to take
this into account.
* UI/Web: Moves the Stop buttons out of the Advanced sections and next
to Generate to make things not fit quite so badly with the extra UI
elements.
* UI/Web: Fixes logging to the upscaler output text box not working
correctly when running multiple batches.
* Adds a button that opens the currently selected subdirectory using
the default OS file manager
* Improve output gallery handling of having images deleted out from
under it.
* Don't show VAE or LoRA lines in parameter info panel when their
value is 'None'
* Use a css class for small icon buttons on the output gallery
tab instead using the same id for multiple buttons
* Clear .style deprecation warnings.
* Re-remove download button from Nod logos.
* Add work around for `container=false` not doing what it did before on
dropdowns to the output gallery CSS
* fixed missing line break in `stablelm_ui.py` `start_message`
- also more formatting changes
* fix variable spelling mistake
* revert some formatting cause black wants it different
* one less line, still less than 79
* add ++, karras, and karras++ types of dpmsolver.
* black line length 79
---------
Co-authored-by: powderluv <powderluv@users.noreply.github.com>
* - fix overflowing text (a janky fix)
- add DEISMultistep scheduler as an option
- set default scheduler to DEISMultistep
- set default CFG to 3.5
- set default steps to 16
- add `xzuyn/PhotoMerge` as a model option
- add 3 new example prompts (which work nicely with PhotoMerge)
- formatting
* Set DEISMultistep in the cpu_only list instead
* formatting
* formatting
* modify prompts
* resize window to 81% & 85% monitor resolution instead of (WxH / 1.0625).
* increase steps to 32 after some testing. somewhere in between 16 and 32 is best compromise on speed/quality for DEIS, so 32 steps to play it safe.
* black line length 79
* revert settings DEIS as default scheduler.
* add more schedulers & revert accidental DDIM change
- add DPMSolverSingleStep, KDPM2AncestralDiscrete, & HeunDiscrete.
- did not add `DPMSolverMultistepInverse` or `DDIMInverse` as they only output latent noise, there are a few I did not try adding yet.
- accidentally set `upscaler_ui.py` to EulerDiscrete by default last commit while reverting DEIS changes.
- add `xzuyn/PhotoMerge-inpainting` as an in or out painting model.
* black line length 79
* add help section stuff and some other changes
- list the rest of the schedulers in argument help section.
- replace mutable default arguments.
- increased default window height to 91% to remove any scrolling for the main txt2img page (tested on a 1920x1080 monitor). width is the same as its just enough to have the image output on the side instead of the bottom.
- cleanup
* Adding metal_utils for iree_utils
* Add patch for making compile API work for both MEGABYTE and MiniGPT4 (#1559)
-- It also modifies the mega_test.py script
Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
* [SD] Update unet in_channels API and add PIL metadata to spec. (#1560)
* Fix deprecation warning for unet config.
* Include PIL metadata instead of hidden imports in SD spec.
* Fixing iree-metal-target-platform
* adding metal to txt2img pipeline
* Fixing Copyright date
* removing debug prints
* black lint formating
* fixing device dump
---------
Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
Co-authored-by: Abhishek Varma <avarma094@gmail.com>
Co-authored-by: Ean Garvey <87458719+monorimet@users.noreply.github.com>
Co-authored-by: powderluv <powderluv@users.noreply.github.com>
* Fixes randomize seed buttons that stopped working.
* Update now deprecated method to set initial colums for output
gallery to the newer undeprecated one.
* On startup report that cleaning up of temp files is taking place, in
case it takes a long time.
* Have the output gallery tab delete any zero length temporary files
generated by gradio < 3.32.0 for its gallery control whenever it
needs to update that control with images. This prevents such
files multiplying out of control.
This fix the gallery component of the output gallery dumping temporary
files into the standard folders rather than shark_tmp so those files never
got cleared out on restart and would build up.
* UI/Web: Fix upscaler stop button
* Hook the cancel_sd function up to the Stop button.
* Adds checks for SD_STATE_CANCEL in the upscaler ui inference function.
* Set and check for SD_STATE_IDLE, SD_STATE_CANCEL in the upscaler
pipeline.
* UI/Web: lint fixes for upscaler stop button fix
---------
Co-authored-by: powderluv <powderluv@users.noreply.github.com>
