Update README.md

README.md

@@ -18,7 +18,7 @@ def _get_qwen3_prompt_embeds(...):
   ...
   image_features = vision_model.get_image_features(image_path)
   output = text_encoder(
-    input_embeds=embedder(image_features),
+    inputs_embeds=embedder(image_features),
     attention_mask=attention_mask,
     output_hidden_states=True,
     use_cache=False,
@@ -37,3 +37,13 @@ pipeline = Flux2KleinPipeline.from_pretrained(flux2_path, torch_dtype=torch.bflo
 - 2510.17800
 - 2510.18279
 - 2601.14251
+
+## Datasets
+
+- artbench-pd-256x256
+- anime-art-multicaptions (multicharacter interactions)
+- laion
+- spatial-caption
+- spright-coco
+- z-image-ethnicity-test
+- benchmarks from the Qwen-Image Technical Report