Update README.md
Browse files
README.md
CHANGED
@@ -29,7 +29,7 @@ widget:
|
|
29 |
pipeline_tag: text2text-generation
|
30 |
---
|
31 |
## t5-small-negative-prompt-generator
|
32 |
-
|
33 |
|
34 |
It achieves the following results on the evaluation set:
|
35 |
* Loss: 0.1730
|
@@ -38,7 +38,7 @@ It achieves the following results on the evaluation set:
|
|
38 |
* Rougel: 62.0977
|
39 |
* Rougelsum: 62.1006
|
40 |
|
41 |
-
The idea behind this is to automatically generate negative prompts that improve the end result according to the positive prompt input.
|
42 |
|
43 |
The license is **cc-by-nc-4.0**. For commercial use rights, please [contact me](https://discord.com/users/859202914400075798).
|
44 |
|
|
|
29 |
pipeline_tag: text2text-generation
|
30 |
---
|
31 |
## t5-small-negative-prompt-generator
|
32 |
+
The model here is [t5-small](https://huggingface.co/google-t5/t5-small) and has been finetuned on a subset of the [AdamCodd/Civitai-8m-prompts](https://huggingface.co/datasets/AdamCodd/Civitai-8m-prompts) dataset (~800K prompts) focused on the top 10% prompts according to Civitai's positive engagement ("stats" field in the dataset). It includes negative embeddings (and thus will output them).
|
33 |
|
34 |
It achieves the following results on the evaluation set:
|
35 |
* Loss: 0.1730
|
|
|
38 |
* Rougel: 62.0977
|
39 |
* Rougelsum: 62.1006
|
40 |
|
41 |
+
The idea behind this is to automatically generate negative prompts that improve the end result according to the positive prompt input. I believe it could be useful as a recommendation for new users who use stable-diffusion or similar.
|
42 |
|
43 |
The license is **cc-by-nc-4.0**. For commercial use rights, please [contact me](https://discord.com/users/859202914400075798).
|
44 |
|