Hugging Face's logo

Anzhc
/
SDXL-Text-Encoder-Longer-CLIP-L

Diffusers
Model card Files
xet
Community
Anzhc commited on
Commit
20ade1c
·
verified ·
1 Parent(s): 7ef754c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -3,4 +3,17 @@ license: openrail
3
  base_model:
4
  - stabilityai/stable-diffusion-xl-base-1.0
5
  library_name: diffusers
6
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  base_model:
4
  - stabilityai/stable-diffusion-xl-base-1.0
5
  library_name: diffusers
6
+ ---
7
+
8
+ An experiment, with CLIP L trained with up to 770 tokens with ~10k anime dataset, without adjusting arch. Concatenation is used to accummulate features.
9
+
10
+ ![output(4)](https://cdn-uploads.huggingface.co/production/uploads/633b43d29fe04b13f46c8988/vOCBqQ4fhIhD157o4QSuO.png)
11
+
12
+ ![output(5)](https://cdn-uploads.huggingface.co/production/uploads/633b43d29fe04b13f46c8988/OBNY_waRMkPR-I_29KN_2.png)
13
+
14
+ Token-adjusted, with images removed if they ca'nt meet token criteria:
15
+
16
+ ![output(6)](https://cdn-uploads.huggingface.co/production/uploads/633b43d29fe04b13f46c8988/fmQfZBgniqdZOTXPynqkO.png)
17
+
18
+ ![output(7)](https://cdn-uploads.huggingface.co/production/uploads/633b43d29fe04b13f46c8988/FnnsQsBGs-LFJFPCebcda.png)
19
+