i

readme.md

@@ -48,7 +48,7 @@ Note that some of these tricks are currently (2023 Aug 11) impossible to reprodu
 3. We modified the style templates a bit and added the "cinematic-default".
 4. We tested the "sd_xl_offset_example-lora_1.0.safetensors" and it seems that when the lora weight is below 0.5, the results are always better than XL without lora.
 5. The parameters of samplers are carefully tuned.
-6. Because XL uses positional encoding for generation resolution, images generated by several fixed resolutions look a bit better than that from arbitrary resolutions (because the positional encoding is not very good at handling int numbers that are unseen during training). This suggests that resolutions in UI may be hard coded for best results.
+6. Because XL uses positional encoding for generation resolution, images generated by several fixed resolutions look a bit better than that from arbitrary resolutions (because the positional encoding is not very good at handling int numbers that are unseen during training). This suggests that the resolutions in UI may be hard coded for best results.
 7. Separated prompts for two different text encoders seem unnecessary. Separated prompts for base model and refiner may work but the effects are random, and we refrain from implement this.
 8. DPM family seems well-suited for XL, since XL sometimes generates overly smooth texture but DPM family sometimes generate overly dense detail in texture. Their joint effect looks neutral and appealing to human perception.