[GammaXL] NSFW for Anything XL
34
219
4
0
Updated: Mar 27, 2024
v1.0
REMIX
❤️
1
0
REMIX
0
Images hidden due to mature content settings
Verified: 2 days ago
SafeTensor
Details
Type
CHECKPOINT TRAINED
Stats
219
Reviews
(34)
Uploaded
Mar 26, 2024
Base Model
SDXL 1.0
Hash
AUTOV2
B19B4B748C
1 File
Full Model fp16 (6.46 GB)
Verified: 2 days ago
SafeTensor
License:
CreativeML Open RAIL++-MAddendum
This model is a NSFW enhanced version of AnythingXL.But this model is not very good at generating pictures of "sexual behavior" and "sexual organs".This model is only made by the author according to his own preferences.
Test model. AnythingXL-Gamma4 was trained on AnythingXL beta4. Changed parts of the model.
The prompt words in the display chart are all generated using DTG, which has nothing to do with the author's own orientation:
KBlueLeaf/DanTagGen-beta · Hugging Face
Formula:
clip(all):
AnythingXL-Gamma4 x 0.8 AnythingXL-Beta4 x 0.2
Unet:
The metadata shows Anything beta4 just because I forgot to change the name and the original beta4 model was overwritten
Anything-beta4 x 0.6 AnythingXL-Gamma4 x 0.4
VAE:
No changes made
Prompts format:
<|special|>, <|characters|>, <|copyrights|>, <|artist|>, <|tags|>, <|quality|>, <|meta|>, <|rating|>
Negative Prompts (Recommended):
nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name
Special tags:
The model can still be used without these special cue words, but incorporating these special tags when necessary can help steer the generated results towards the desired direction.
years:
These words help guide the results towards modern and retro anime art styles, with a specific timeframe of approximately 2005 to 2023
old 2005~? mid ?~? newest ?~2024
NSFW:
These words help guide the results towards ***** content, but generally do not generate ***** content if rating words are not included.
Of course, you can also put it in negative prompts.
safe General sensitive Sensitive nsfw Questionable explicit, nsfw Explicit
quality:
While this model can function without quality words, in practice, these words can still be used to adjust the output.