InvokeAI/ldm/invoke/generator
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
..
__init__.py rename all modules from ldm.dream to ldm.invoke 2022-10-08 11:37:23 -04:00
base.py cleanup inpainting and img2img 2022-10-16 08:50:55 -04:00
embiggen.py rename all modules from ldm.dream to ldm.invoke 2022-10-08 11:37:23 -04:00
img2img.py ported code refactor changes from PR #1221 2022-10-23 09:33:15 -04:00
inpaint.py ported code refactor changes from PR #1221 2022-10-23 09:33:15 -04:00
txt2img2img.py rename all modules from ldm.dream to ldm.invoke 2022-10-08 11:37:23 -04:00
txt2img.py add clipseg support for creating inpaint masks from text 2022-10-18 08:27:48 -04:00