Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ tags:
|
|
| 21 |
|
| 22 |
<hr>
|
| 23 |
|
| 24 |
-
|
| 25 |
|
| 26 |
**For ComfyUI**
|
| 27 |
|
|
@@ -37,7 +37,7 @@ Additionally, the repository contains two workflows for use in **ComfyUI**: [Rea
|
|
| 37 |
|
| 38 |
<hr>
|
| 39 |
|
| 40 |
-
|
| 41 |
- While this model can handle long prompts, you may observe artifacts on the edge of generations when T5 tokens go over 256. Pay attention to the token limits when using this model in your workflow, and shortern prompts if artifacts becomes too obvious.
|
| 42 |
- The medium model has a different training data distribution than the large model, so it may not respond to the same prompt similarly.
|
| 43 |
- We recommend sampling with **[Skip Layer Guidance](https://github.com/comfyanonymous/ComfyUI/pull/5404)** for better structure and anatomy coherency.
|
|
|
|
| 21 |
|
| 22 |
<hr>
|
| 23 |
|
| 24 |
+
# How to Use
|
| 25 |
|
| 26 |
**For ComfyUI**
|
| 27 |
|
|
|
|
| 37 |
|
| 38 |
<hr>
|
| 39 |
|
| 40 |
+
# Usage & Limitations
|
| 41 |
- While this model can handle long prompts, you may observe artifacts on the edge of generations when T5 tokens go over 256. Pay attention to the token limits when using this model in your workflow, and shortern prompts if artifacts becomes too obvious.
|
| 42 |
- The medium model has a different training data distribution than the large model, so it may not respond to the same prompt similarly.
|
| 43 |
- We recommend sampling with **[Skip Layer Guidance](https://github.com/comfyanonymous/ComfyUI/pull/5404)** for better structure and anatomy coherency.
|