Commit Graph

1173 Commits

Author SHA1 Message Date
psychedelicious
d923d1d66b fix(nodes): fix naming of CvInvocationConfig 2023-04-11 12:13:53 +10:00
psychedelicious
1f2c1e14db fix(nodes): move InvocationConfig to baseinvocation.py 2023-04-11 12:13:53 +10:00
psychedelicious
07e3a0ec15 feat(nodes): add invocation schema customisation, add model selection
- add invocation schema customisation

done via fastapi's `Config` class and `schema_extra`. when using `Config`, inherit from `InvocationConfig` to get type hints.

where it makes sense - like for all math invocations - define a `MathInvocationConfig` class and have all invocations inherit from it.

this customisation can provide any arbitrary additional data to the UI. currently it provides tags and field type hints.

this is necessary for `model` type fields, which are actually string fields. without something like this, we can't reliably differentiate  `model` fields from normal `string` fields.

can also be used for future field types.

all invocations now have tags, and all `model` fields have ui type hints.

- fix model handling for invocations

added a helper to fall back to the default model if an invalid model name is chosen. model names in graphs now work.

- fix latents progress callback

noticed this wasn't correct while working on everything else.
2023-04-11 12:13:53 +10:00
psychedelicious
427db7c7e2 feat(nodes): fix typo in PasteImageInvocation 2023-04-10 21:33:08 +10:00
psychedelicious
dad3a7f263 fix(nodes): sampler_name --> scheduler
the name of this was changed at some point. nodes still used the old name, so scheduler selection did nothing. simple fix.
2023-04-10 19:54:09 +10:00
psychedelicious
34402cc46a feat(nodes): add list_images endpoint
- add `list_images` endpoint at `GET api/v1/images`
- extend `ImageStorageBase` with `list()` method, implemented it for `DiskImageStorage`
- add `ImageReponse` class to for image responses, which includes urls, metadata
- add `ImageMetadata` class (basically a stub at the moment)
- uploaded images now named `"{uuid}_{timestamp}.png"`
- add `models` modules. besides separating concerns more clearly, this helps to mitigate circular dependencies
- improve thumbnail handling
2023-04-09 13:48:44 +10:00
psychedelicious
111d674e71 fix(nodes): use correct torch device in NoiseInvocation 2023-04-08 12:32:03 +10:00
Kyle Schouviller
85b020f76c
[nodes] Add latent nodes, storage, and fix iteration bugs (#3091)
* Add latents nodes.
* Fix iteration expansion.
* Add collection generator nodes, math nodes.
* Add noise node.
* Add some graph debug commands to the CLI.
* Fix negative id linking in CLI.
* Fix a CLI bug with multiple links per node.
2023-04-06 04:06:05 +00:00
psychedelicious
4221cf7731 fix(nodes): fix schema generation for output classes
All output classes need to have their properties flagged as `required` for the schema generation to work as needed.
2023-03-26 17:20:10 +11:00
psychedelicious
c34ac91ff0 fix(nodes): fix cancel; fix callback for img2img, inpaint 2023-03-26 17:07:40 +11:00
Lincoln Stein
dac3c158a5 Merge branch 'main' into feat/preview_predicted_x0
- resolve conflicts with generate.py invocation
- remove unused symbols that pyflakes complains about
- add **untested** code for passing intermediate latent image to the
  step callback in the format expected.
2023-03-25 16:07:18 -04:00
psychedelicious
67f8f222d9 fix(nodes): fix step_callback + fast latents generation
this depends on the small change in #2957
2023-03-16 20:03:08 +11:00
Kyle Schouviller
0c3b1fe3c4 [nodes] Fixes calls into image to image and inpaint from nodes 2023-03-12 22:12:42 -07:00
Kevin Turner
288cee9611 Merge remote-tracking branch 'origin/main' into feat/preview_predicted_x0
# Conflicts:
#	invokeai/app/invocations/generate.py
2023-03-12 20:56:02 -07:00
Lincoln Stein
8ca91b1774 add restoration services to nodes 2023-03-11 17:00:00 -05:00
Lincoln Stein
d612f11c11 initialize InvokeAIGenerator object with model, not manager 2023-03-11 09:06:46 -05:00
Lincoln Stein
95954188b2 remove factory pattern
Factory pattern is now removed. Typical usage of the InvokeAIGenerator is now:

```
from invokeai.backend.generator import (
    InvokeAIGeneratorBasicParams,
    Txt2Img,
    Img2Img,
    Inpaint,
)
    params = InvokeAIGeneratorBasicParams(
        model_name = 'stable-diffusion-1.5',
        steps = 30,
        scheduler = 'k_lms',
        cfg_scale = 8.0,
        height = 640,
        width = 640
        )
    print ('=== TXT2IMG TEST ===')
    txt2img = Txt2Img(manager, params)
    outputs = txt2img.generate(prompt='banana sushi', iterations=2)

    for i in outputs:
        print(f'image={output.image}, seed={output.seed}, model={output.params.model_name}, hash={output.model_hash}, steps={output.params.steps}')
```

The `params` argument is optional, so if you wish to accept default
parameters and selectively override them, just do this:

```
    outputs = Txt2Img(manager).generate(prompt='banana sushi',
                                        steps=50,
					scheduler='k_heun',
					model_name='stable-diffusion-2.1'
					)
```
2023-03-10 19:33:04 -05:00
Kevin Turner
fe6858f2d9 feat: use the predicted denoised image for previews
Some schedulers report not only the noisy latents at the current timestep,
but also their estimate so far of what the de-noised latents will be.

It makes for a more legible preview than the noisy latents do.
2023-03-09 20:28:06 -08:00
Lincoln Stein
5d37fa6e36 node-based txt2img working without generate 2023-03-09 00:18:29 -05:00
Lincoln Stein
ab35c241c2 protect invocations against black autoformatting 2023-03-03 15:25:08 -05:00
Lincoln Stein
6477e31c1e revert and disable auto-formatting of invocations 2023-03-03 14:59:17 -05:00
Lincoln Stein
60a98cacef all vestiges of ldm.invoke removed 2023-03-03 01:02:00 -05:00
Lincoln Stein
6a990565ff all files migrated; tweaks needed 2023-03-03 00:02:15 -05:00