H&A Models
commited on
Commit
·
82df3cf
1
Parent(s):
918ffff
Update README.md
Browse files
README.md
CHANGED
|
@@ -29,12 +29,12 @@ Our aim is to provide a useful tool that can produce consistent and high-resolut
|
|
| 29 |
|
| 30 |
<!-- 3DKX is a model that was trained on highly detailed 3D rendered pictures of various subjects such as landscapes, scenes, models, textures, and more.
|
| 31 |
Our aim is to provide a useful tool that can produce consistent and high-resolution renders for creative purposes such as storyboarding, sketching, templates, wallpapers, and more. -->
|
| 32 |
-
3D renders, cartoony or realistic
|
| 33 |
-
Landscapes
|
| 34 |
-
Scenery
|
| 35 |
-
Fantasy, creatures, RPG renders
|
| 36 |
-
Portraits
|
| 37 |
-
Dramatic scenes, horror, dark, obscure
|
| 38 |
|
| 39 |
## Get started with the model, use our cheat sheet !
|
| 40 |
|
|
@@ -42,14 +42,6 @@ Use the guide in the link below to get started with the model !
|
|
| 42 |
|
| 43 |
[More Information Needed]
|
| 44 |
|
| 45 |
-
# Training Details
|
| 46 |
-
|
| 47 |
-
## Training Procedure
|
| 48 |
-
|
| 49 |
-
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 50 |
-
Big shoutout to this new code that allowed us to fix the diffusion noise, allowing for more depth, contrast, and white level balance in the outputs.
|
| 51 |
-
https://www.crosslabs.org//blog/diffusion-with-offset-noise
|
| 52 |
-
|
| 53 |
## Results
|
| 54 |
|
| 55 |
[More Information Needed]
|
|
@@ -76,4 +68,10 @@ You agree not to use the Model or Derivatives of the Model:
|
|
| 76 |
- The purpose of this model isn't to replicate a style, but to provide a useful tool to creators of all kinds to generate 3D related contents
|
| 77 |
- Be advised that this model can generate explicit material and therefore shouldn't be used in any way to cause harm or produce non-consensual sexual content.
|
| 78 |
|
|
|
|
|
|
|
|
|
|
| 79 |
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
<!-- 3DKX is a model that was trained on highly detailed 3D rendered pictures of various subjects such as landscapes, scenes, models, textures, and more.
|
| 31 |
Our aim is to provide a useful tool that can produce consistent and high-resolution renders for creative purposes such as storyboarding, sketching, templates, wallpapers, and more. -->
|
| 32 |
+
- 3D renders, cartoony or realistic
|
| 33 |
+
- Landscapes
|
| 34 |
+
- Scenery
|
| 35 |
+
- Fantasy, creatures, RPG renders
|
| 36 |
+
- Portraits
|
| 37 |
+
- Dramatic scenes, horror, dark, obscure
|
| 38 |
|
| 39 |
## Get started with the model, use our cheat sheet !
|
| 40 |
|
|
|
|
| 42 |
|
| 43 |
[More Information Needed]
|
| 44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
## Results
|
| 46 |
|
| 47 |
[More Information Needed]
|
|
|
|
| 68 |
- The purpose of this model isn't to replicate a style, but to provide a useful tool to creators of all kinds to generate 3D related contents
|
| 69 |
- Be advised that this model can generate explicit material and therefore shouldn't be used in any way to cause harm or produce non-consensual sexual content.
|
| 70 |
|
| 71 |
+
# Training Details
|
| 72 |
+
|
| 73 |
+
## Training Procedure
|
| 74 |
|
| 75 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 76 |
+
Big shoutout to this new code that allowed us to fix the diffusion noise, allowing for more depth, contrast, and white level balance in the outputs.
|
| 77 |
+
https://www.crosslabs.org//blog/diffusion-with-offset-noise
|