Update README.md

README.md

@@ -34,7 +34,9 @@ Normal K-quants are not working properly with SD3.5-Large models because around
 
 ## Outputs:
 
-| Name               | Image                            | Image                              | Image                              |
+Sorted by model size (Note that q4_0 and q4_k_4_0 are the exact same size)
+
+| Quantization       | Robot girl                       | Text                               | Cute kitten                        |
 | ------------------ | -------------------------------- | ---------------------------------- | ---------------------------------- |
 | q2_k_4_0           | ![q2_k_4_0](Images/q2_k_4_0.png) | ![q2_k_4_0](Images/1_q2_k_4_0.png) | ![q2_k_4_0](Images/2_q2_k_4_0.png) |
 | q3_k_4_0           | ![q3_k_4_0](Images/q3_k_4_0.png) | ![q3_k_4_0](Images/1_q3_k_4_0.png) | ![q3_k_4_0](Images/2_q3_k_4_0.png) |
@@ -47,3 +49,7 @@ Normal K-quants are not working properly with SD3.5-Large models because around
 | q5_1               | ![q5_1](Images/q5_1.png)         | ![q5_1](Images/1_q5_1.png)         | ![q5_1](Images/2_q5_1.png)         |
 | q8_0               | ![q8_0](Images/q8_0.png)         | ![q8_0](Images/1_q8_0.png)         | ![q8_0](Images/2_q8_0.png)         |
 | f16(sft)           | ![f16](Images/f16.png)           | ![f16](Images/1_f16.png)           | ![f16](Images/2_f16.png)           |
+
+Using q4_k version of t5xxl, full precision clip_g, and q8 quant of [ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF](https://huggingface.co/zer0int/CLIP-GmP-ViT-L-14) in place of clip_l.
+
+Full prompts and settings in png metadata.