Update README.md

README.md

@@ -42,21 +42,21 @@ Various experiments, some decent, some bad. Trained on publicly accessible image
 **Pretty good** but the originals tended to gravitate towards a certain size in the chest area and it can be difficult to change that aspect.
 
 **digital painting**  
-144 * 2048px images, 1024px, 1536px and 2048px buckets. Short captions generated with some old LLM.  
+144 * 2048px images, 1024px and 1536px buckets. Short captions generated with some old LLM.  
 **Pretty bad** - details look sharp but the style is inconsistent.
 
 **digital painting v2**  
-72 * 1024px images, 1024px buckets. Very long captions generated with Qwen3-VL-32B-Instruct.  
-**Decent** - details look slightly worse than v1 but the style is much more consistent. I'd probably use even fewer images but of higher quality for v3 and train with only 1536px buckets and shorter captions.
+72 * 2048px images, 1024px buckets. Very long captions generated with Qwen3-VL-32B-Instruct.  
+**Decent** - details look slightly worse than v1 but the style is much more consistent. I'd probably use even fewer images for v3 but train with 1536px buckets and shorter captions.
 
 **game art**  
 270 * 1024px images extracted from a certain cute and funny game, 1024px buckets, very long Qwen3-VL-32B captions.  
 **Very bad** - way too many images, looks like it averaged the style instead of learning it. Definitely fewer images for v2 and maybe shorter captions.
 
 **ink art**  
-82 * 2048px images, 1024px, 1536px and 2048px buckets, very long Qwen3-VL-32B captions.  
+82 * 2048px images, 1024px and 1536px buckets, very long Qwen3-VL-32B captions.  
 **Bad** - very inconsistent at applying the style, seems to work better at higher resolutions. Same recommendations as above.
 
 **oil painting**  
-60 * 2048px images, 1024px, 1536px and 2048px buckets. Short captions generated with some old LLM.  
+60 * 2048px images, 1024px and 1536px buckets. Short captions generated with some old LLM.  
 **Good** - no real complaints. I tried training a v2 with longer captions but it didn't change much. The style seems very easy for the model to grasp.