Commit Graph

13 Commits

Author SHA1 Message Date
Lincoln Stein
e33971fe2c plms works, bugs quashed
- The plms sampler now works with custom inpainting model
- Quashed bug that was causing generation on normal models to fail (oops!)
- Can now generate non-square images with custom inpainting model

Credits for advice and assistance during porting:

@any-winter-4079 (http://github.com/any-winter-4079)
@db3000 (Danny Beer http://github.com/db3000)
2022-10-25 11:44:01 -04:00
Lincoln Stein
b101be041b add support for runwayML custom inpainting model
This is still a work in progress but seems functional. It supports
inpainting, txt2img and img2img on the ddim and k* samplers (plms
still needs work, but I know what to do).

To test this, get the file `sd-v1-5-inpainting.ckpt' from
https://huggingface.co/runwayml/stable-diffusion-inpainting and place it
at `models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt`

Launch invoke.py with --model inpainting-1.5 and proceed as usual.

Caveats:

1. The inpainting model takes about 800 Mb more memory than the standard
   1.5 model. This model will not work on 4 GB cards.

2. The inpainting model is temperamental. It wants you to describe the
   entire scene and not just the masked area to replace. So if you want
   to replace the parrot on a man's shoulder with a crow, the prompt
   "crow" may fail. Try "man with a crow on shoulder" instead. The
   symptom of a failed inpainting is that the area will be erased and
   replaced with background.

3. This has not been tested well. Please report bugs.
2022-10-25 10:45:15 -04:00
Lincoln Stein
aaf7a4f1d3 inpaint and txt2img working with ddim sampler 2022-10-25 10:00:28 -04:00
Lincoln Stein
a2e53892ec fixed synax errors; now channel mismatch issue 2022-10-25 00:47:13 -04:00
Lincoln Stein
be8a992b85 add missing file 2022-10-25 00:38:24 -04:00
Lincoln Stein
83a3cc9eb4 start support for 1.5 inpainting model, not complete 2022-10-25 00:30:48 -04:00
Lincoln Stein
5561a95232 inpainting fix per PR #1218
- This is a merge of the final version of PR #1218 "Inpainting
  Improvements"

  Various merge conflicts made it easier to commit directly.

Author: Kyle0654
Co-Author: lstein
2022-10-23 22:52:32 -04:00
Lincoln Stein
7e27f189cf minor fixes to inpaint code
1. If tensors are passed to inpaint as init_image and/or init_mask, then
   the post-generation image fixup code will be skipped.

2. Post-generation image fixup will work with either a black and white "L"
   or "RGB"  mask, or an "RGBA" mask.
2022-10-23 09:33:15 -04:00
Lincoln Stein
9472945299 ported code refactor changes from PR #1221
- pass a PIL.Image to img2img and inpaint rather than tensor
- To support clipseg, inpaint needs to accept an "L" or "1" format
  mask. Made the appropriate change.
2022-10-23 09:33:15 -04:00
Kyle Schouviller
493eaa7389 Improve inpainting by color-correcting result and pasting init image over result using mask 2022-10-23 09:33:15 -04:00
Lincoln Stein
20551857da add clipseg support for creating inpaint masks from text
On the command line, the new option is --text_mask or -tm.
Example:

```
invoke> a baseball -I /path/to/still_life.png -tm orange
```

This will find the orange fruit in the still life painting and replace
it with an image of a baseball.
2022-10-18 08:27:48 -04:00
Lincoln Stein
6f93dc7712 cleanup inpainting and img2img
- add a `--inpaint_replace` option that fills masked regions with
  latent noise. This allows radical changes to inpainted regions
  at the cost of losing context.
- fix up readline, arg processing and metadata writing to accommodate
  this change
- fixed bug in storage and retrieval of variations, discovered incidentally
  during testing
- update documentation
2022-10-16 08:50:55 -04:00
Lincoln Stein
2b1aaf4ee7 rename all modules from ldm.dream to ldm.invoke
- scripts and documentation updated to match
- ran preflight checks on both web and CLI and seems to be working
2022-10-08 11:37:23 -04:00