InvokeAI/TODO.txt
2022-08-26 14:59:53 -04:00

36 lines
1.1 KiB
Plaintext

Feature requests:
1. "gobig" mode - split image into strips, scale up, add detail using - DONE!
img2img and reassemble with feathering. Issue #66.
See https://github.com/jquesnelle/txt2imghd
2. Port basujindal low VRAM optimizations. Issue #62
3. Store images under folders named after the prompt. Issue #27.
4. Some sort of automation for generating variations. Issues #32 and #47.
5. Support for inpainting masks #68.
6. Support for loading variations of the stable-diffusion
weights #49
7. Support for klms and other non-ddim samplers in img2img() #36 - DONE!
8. Pass a shell command to open up an image viewer on the last
batch of images generated #29.
9. Change sampler and outdir after initialization #115
Code Refactorization:
1. Move the PNG file generation code out of simplet2i and into - DONE!
separate module. txt2img() and img2img() should return Image
objects, and parent code is responsible for filenaming logic.
2. Refactor redundant code that is shared between txt2img() and - DONE!
img2img().
3. Experiment with replacing CompViz code with HuggingFace. - NOT WORTH IT!