Update README.md
Browse files
README.md
CHANGED
|
@@ -13,11 +13,11 @@ tags:
|
|
| 13 |
library_name: diffusers
|
| 14 |
pipeline_tag: text-to-image
|
| 15 |
---
|
| 16 |
-
# Most checkpoints are default sd15 after testing
|
| 17 |
-
The CURRENT e8 has no clip or vae, so it's just sitting there standalone.
|
| 18 |
-
|
| 19 |
For those who downloaded the models that either exhibit blobs or don't use flow matching noise - my sincerest apologies. They are defective.
|
| 20 |
|
|
|
|
|
|
|
| 21 |
I removed the faulty checkpoints and the correct checkpoints are the only ones remaining, which are early training and incompatible with correct inference, will be present.
|
| 22 |
|
| 23 |
# Updated information
|
|
|
|
| 13 |
library_name: diffusers
|
| 14 |
pipeline_tag: text-to-image
|
| 15 |
---
|
| 16 |
+
# Most original checkpoints are default sd15 after testing
|
|
|
|
|
|
|
| 17 |
For those who downloaded the models that either exhibit blobs or don't use flow matching noise - my sincerest apologies. They are defective.
|
| 18 |
|
| 19 |
+
The CURRENT e8 has no clip or vae, so it's just sitting there standalone. This is the currently newest valid one and it functions as expected - by making blobs due to early pretraining.
|
| 20 |
+
|
| 21 |
I removed the faulty checkpoints and the correct checkpoints are the only ones remaining, which are early training and incompatible with correct inference, will be present.
|
| 22 |
|
| 23 |
# Updated information
|