Update README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
---
|
| 4 |
|
| 5 |
-
##
|
| 6 |
|
| 7 |
Token and Class words are what guide the AI to produce images similar to the trained style/object/character.
|
| 8 |
Include any mix of these words in the prompt to produce verying results, or exclude them to have a less pronounced effect.
|
|
@@ -15,7 +15,13 @@ However it can be also very prompt specific. I highly recommend self-experimenta
|
|
| 15 |
|
| 16 |
These models are subject to the same legal concerns as their base models.
|
| 17 |
|
| 18 |
-
##
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
```
|
| 20 |
token: m_aeolian
|
| 21 |
class: §¶•
|
|
@@ -23,7 +29,7 @@ base: waifu diffusion 1.2-e5
|
|
| 23 |
notes: 2020 step training
|
| 24 |
```
|
| 25 |
|
| 26 |
-
##
|
| 27 |
```
|
| 28 |
token: m_aeolian
|
| 29 |
class: §¶•
|
|
@@ -31,10 +37,20 @@ base: waifu diffusion 1.2-e6
|
|
| 31 |
notes: 3000 step training
|
| 32 |
```
|
| 33 |
|
| 34 |
-
##
|
| 35 |
```
|
| 36 |
token: m_concept
|
| 37 |
class: §
|
| 38 |
base: waifu diffusion 1.3
|
| 39 |
notes: 1.3 model, which may give some benefits over 1.2-e5
|
| 40 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: creativeml-openrail-m
|
| 3 |
---
|
| 4 |
|
| 5 |
+
## Basic explanation
|
| 6 |
|
| 7 |
Token and Class words are what guide the AI to produce images similar to the trained style/object/character.
|
| 8 |
Include any mix of these words in the prompt to produce verying results, or exclude them to have a less pronounced effect.
|
|
|
|
| 15 |
|
| 16 |
These models are subject to the same legal concerns as their base models.
|
| 17 |
|
| 18 |
+
## Comparison
|
| 19 |
+
|
| 20 |
+
Aeolian and aeolian_3000 are quite similar with slight differences.
|
| 21 |
+
|
| 22 |
+
Epoch 5 and 6 versions were earlier in the waifu diffusion 1.3 training process, so it is easier to produce more varied, non anime, results.
|
| 23 |
+
|
| 24 |
+
## aeolian
|
| 25 |
```
|
| 26 |
token: m_aeolian
|
| 27 |
class: §¶•
|
|
|
|
| 29 |
notes: 2020 step training
|
| 30 |
```
|
| 31 |
|
| 32 |
+
## aeolian_3000
|
| 33 |
```
|
| 34 |
token: m_aeolian
|
| 35 |
class: §¶•
|
|
|
|
| 37 |
notes: 3000 step training
|
| 38 |
```
|
| 39 |
|
| 40 |
+
## aeolian_v2
|
| 41 |
```
|
| 42 |
token: m_concept
|
| 43 |
class: §
|
| 44 |
base: waifu diffusion 1.3
|
| 45 |
notes: 1.3 model, which may give some benefits over 1.2-e5
|
| 46 |
```
|
| 47 |
+
|
| 48 |
+
## License
|
| 49 |
+
|
| 50 |
+
This embedding is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
|
| 51 |
+
The CreativeML OpenRAIL License specifies:
|
| 52 |
+
|
| 53 |
+
1. You can't use the embedding to deliberately produce nor share illegal or harmful outputs or content
|
| 54 |
+
2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
|
| 55 |
+
3. You may re-distribute the weights and use the embedding commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully)
|
| 56 |
+
[Please read the full license here](https://huggingface.co/spaces/CompVis/stable-diffusion-license)
|