Added samples to model card

README.md

@@ -17,19 +17,22 @@ also need the **Qwen3-VL text encoder and VAE** from the base repo [`ideogram-ai
 and the custom inference code at [`github.com/ideogram-oss/ideogram4`](https://github.com/ideogram-oss/ideogram4).
 The quantization recipe and loader are included **in this repo** (`recipe.json`, `safetensors_loader.py`).
 
-## Why this one
+## Why INT8
 INT8 **holds the FP8 quality ceiling**: on a 200-prompt benchmark the paired same-seed
 bootstrap CI for INT8−FP8 includes zero on both Pick and CLIP (statistically
 indistinguishable at this sample size), and it beats NF4 by **+1.9 CLIP** (CI excludes
 zero). Text rendering stays legible (OCR NED 0.704 vs NF4 0.760).
 
+## Samples
+![image (8)](https://cdn-uploads.huggingface.co/production/uploads/6316131329411a6864b13751/1gGu1ZK500Sw4F02Qofil.png)
+
 ## Method
 Per-channel int8 weights + per-token dynamic int8 activations + SmoothQuant (α=0.5) +
 mixed-precision protection of the **top-17 fragility-prone layers** (the FFN
 down-projections, ~8% of linears), kept in bf16. See `recipe.json` for the exact module
 list and tensor layout.
 
-## Honest notes
+## Notes
 - On-disk **~20.4 GB** — at 8-bit weights this is **FP8-class in size, not smaller than
   NF4** (10.4 GB). Its win is *quality*, not memory.
 - Without a fused Ampere INT8 GEMM it runs ~184 s/img (no speed win yet); a custom-kernel