docs: update model card — 5000-step run, scale=3.0 recommendation

README.md

@@ -34,7 +34,7 @@ A **PEFT LoRA adapter** trained on top of [Tongyi-MAI/Z-Image-Turbo](https://hug
 | Target modules | `to_q`, `to_k`, `to_v`, `w1`, `w2`, `w3` |
 | Trainable params | ~39 M |
 | Adapter size | ~271 MB |
-| Training steps | 3 000 |
+| Training steps | **5 000** (3 000 at lr=1e-4 + 2 000 continued at lr=5e-5, EMA) |
 | Training resolution | 512 × 512 |
 | Dataset | [DownFlow/fuliji](https://huggingface.co/datasets/DownFlow/fuliji) (8 artists, ~200 images) |
 
@@ -89,10 +89,10 @@ PEFT exposes a scaling multiplier per adapter. Increase it to push the style har
 # After PeftModel.from_pretrained ...
 for module in pipe.transformer.modules():
     if hasattr(module, "scaling"):
-        module.scaling = {k: v * 1.5 for k, v in module.scaling.items()}
+        module.scaling = {k: v * 3.0 for k, v in module.scaling.items()}
 ```
 
-Recommended range: **1.0 – 2.0**. Values above 3.0 may cause colour artefacts.
+Recommended value: **3.0** (step-5000 EMA, strong identity with no colour artefacts on 8-step inference). Lighter alternative: 1.2. Values above 5 may saturate style.
 
 ---
 
@@ -224,8 +224,8 @@ Prepend `by <artist>, ` at the start of your prompt.
 - **Base model**: `Tongyi-MAI/Z-Image-Turbo` (8-step flow matching, CFG-free)
 - **Method**: PEFT LoRA, rank=32, alpha=32, dropout=0.05
 - **Dataset**: `DownFlow/fuliji` filtered to artists with ≥ 21 images
-- **Steps**: 3 000 with EMA (decay=0.9999)
-- **Optimizer**: AdamW, lr=1e-4, warmup=100 steps
+- **Steps**: **5 000** — 3 000 initial (lr=1e-4) + 2 000 continuation (lr=5e-5, resumed from step 3000 EMA)
+- **Optimizer**: AdamW, lr=1e-4→5e-5, warmup=100 steps each phase
 - **Batch**: 1 × 4 gradient accumulation = effective batch 4
 - **Augmentation**: horizontal flip, caption dropout 5%, timestep bias 1.2
 - **Regularisation**: 25% of batches sample from a 277-image generic dataset