Show sample images in model card

README.md

@@ -75,6 +75,26 @@ worst quality, low quality, score_1, score_2, score_3, artist name
 
 Use lowercase tags with spaces instead of underscores, except score tags such as `score_7`. For artist tags, prefix the artist with `@`.
 
+
+## Sample Output
+
+Comparison generated from the public Diffusers checkpoints:
+
+![Anima SDNQ uint4 vs int8 comparison](images/anima_sdnq_pair_seed_424242_768x768.png)
+
+This checkpoint sample:
+
+![Anima SDNQ int8 sample](images/anima_int8_seed_424242_768x768.png)
+
+Generation settings:
+
+- Prompt: `masterpiece, best quality, score_7, safe, 1girl, fern (sousou no frieren), purple hair, purple eyes, black robe, white dress, butterfly on hand, simple background, looking at viewer`
+- Negative prompt: `worst quality, low quality, score_1, score_2, score_3, blurry, jpeg artifacts, artist name`
+- Seed: `424242`
+- Size: `768x768`
+- Steps: `24`
+- CFG: `4.0`
+
 ## Notes
 
 The original Anima split checkpoint is a ComfyUI-native model with a Qwen3 text encoder and a learned LLM adapter. Earlier transformer-only exports that load the checkpoint directly as `CosmosTransformer3DModel` ignore the `llm_adapter.*` weights; this repo keeps the adapter and full pipeline structure so generation follows the Anima architecture.