Since the Pony model and the SDXL model are very different, I trained the Pony version of DeepNegative
Modellquelle
Quellenbeschreibung
Since the Pony model and the SDXL model are very different, I trained the Pony version of DeepNegative
How to use it?
put it in negative prompt.
another deep-negative:
1.5 version: https://civitai.com/models/4629
SDXL version: https://civitai.com/models/407448
What does it do?
Quellen
1 QuelleModellartefakte
1 Artefaktdeep_negative_pony.safetensors
safetensors · 257 KB · SHA-256 4dd0e783ca77…1488 · Civitai
HerunterladenQuellenauszüge
2 AuszügeSource context: 21658 downloads · Type TextualInversion · Base model Pony
DeepNegative is a negative embedding. it contain unsightly compositions and color patterns, such as inaccurate human anatomy, distasteful color combinations, disoriented spatial structures, and more. By put it in negative prompt, we can significantly reduce the occurrence of these elements.
Suggestion
Because this embedding is learning how to create disgusting concepts , it cannot improve the picture quality accurately, so it is best used with (worst quality, low quality, logo, text, watermark, username:1) these negative prompts.
Of course, it is completely fine to use with other similar negative embeddings.
backup on huggingface
Source context: 21231 downloads · Type TextualInversion · Base model Pony