diff --git a/README.md b/README.md
index 1f0053d..4f622a4 100644
--- a/README.md
+++ b/README.md
@@ -123,10 +123,9 @@ You can use `{}` to randomly pull values from lists. A list of values separated
`imagine "a {lime|blue|silver|aqua} colored dog" -r 2 --seed 0` will generate both "a red dog" and "a black dog"
-
-
-
-
+
+
+
`imagine "a {_color_} dog" -r 4 --seed 0` will generate four, different colored dogs. The colors will eb pulled from an included
phraselist of colors.
@@ -362,10 +361,13 @@ would be uncorrelated to the rest of the surrounding image. It created terrible
- ✅ codeformer - https://github.com/sczhou/CodeFormer
- ✅ image describe feature -
- ✅ https://github.com/salesforce/BLIP
- - https://github.com/rmokady/CLIP_prefix_caption
- - https://github.com/pharmapsychotic/clip-interrogator (blip + clip)
+ - 🚫 CLIP brute-force prompt reconstruction
+ - The accuracy of this approach is too low for me to include it in imaginAIry
+ - https://github.com/rmokady/CLIP_prefix_caption
+ - https://github.com/pharmapsychotic/clip-interrogator (blip + clip)
- https://github.com/KaiyangZhou/CoOp
- - CPU support
+ - 🚫 CPU support. While the code does actually work on some CPUs, the generation takes so long that I don't think it's
+ worth the effort to support this feature
- ✅ img2img for plms
- img2img for kdiff functions
- Other
diff --git a/setup.py b/setup.py
index 6bfc0ac..37a6f9c 100644
--- a/setup.py
+++ b/setup.py
@@ -7,7 +7,7 @@ setup(
name="imaginAIry",
author="Bryce Drennan",
# author_email="b r y p y d o t io",
- version="2.3.1",
+ version="2.4.0",
description="AI imagined images. Pythonic generation of stable diffusion images.",
long_description=readme,
long_description_content_type="text/markdown",