Rename displayed model name to ViTeX-Edit-14B in the model card

README heading, file-tree comments, and the Composite-variant
section heading all switched. Same change applied to the docstrings
of inference_example.py and make_corp_baseline.py and to the
'Loading ... trained weights' log line. Repository URL, the bundled
weights filename (vitex_14b.safetensors), and the local clone target
directory are intentionally unchanged.

README.md

@@ -8,7 +8,7 @@ tags:
   - diffusion
 ---
 
-# ViTeX-14B (Model & Inference code)
+# ViTeX-Edit-14B (Model & Inference code)
 
 🌐 [Project page](https://vitex-bench.github.io/)  · 
 📊 [Dataset](https://huggingface.co/datasets/ViTeX-Bench/ViTeX-Dataset)  · 
@@ -34,8 +34,8 @@ Open reference model for **video scene text editing**. Augments Wan2.1-VACE-14B
 
 ```
 .
-├── inference_example.py            run ViTeX-14B on one (video, mask, glyph) tuple
-├── make_corp_baseline.py           build the ViTeX-14B (Composite) variant
+├── inference_example.py            run ViTeX-Edit-14B on one (video, mask, glyph) tuple
+├── make_corp_baseline.py           build the ViTeX-Edit-14B (Composite) variant
 ├── vitex_14b.safetensors           (8 GB, trained adapter weights)
 ├── diffsynth/                      bundled inference library
 └── base_model/                     (70 GB, frozen DiT + T5-XXL + Wan VAE)
@@ -68,9 +68,9 @@ python inference_example.py \
     --output       out.mp4
 ```
 
-## Locality-preserving variant: ViTeX-14B (Composite)
+## Locality-preserving variant: ViTeX-Edit-14B (Composite)
 
-`make_corp_baseline.py` is a deterministic, training-free post-processing wrapper. Two per-frame operations: (1) Reinhard mean–variance LAB color matching against the source's local lighting; (2) signed-distance feathered alpha compositing onto the source. Inside the mask the result is the predicted glyphs (color-matched); outside the feather it is byte-identical to the source. Locality metrics rise to near-Identity while SeqAcc / CharAcc move within ~0.01 of raw ViTeX-14B.
+`make_corp_baseline.py` is a deterministic, training-free post-processing wrapper. Two per-frame operations: (1) Reinhard mean–variance LAB color matching against the source's local lighting; (2) signed-distance feathered alpha compositing onto the source. Inside the mask the result is the predicted glyphs (color-matched); outside the feather it is byte-identical to the source. Locality metrics rise to near-Identity while SeqAcc / CharAcc move within ~0.01 of raw ViTeX-Edit-14B.
 
 ```bash
 python make_corp_baseline.py \

inference_example.py

@@ -1,5 +1,5 @@
 """
-ViTeX-14B inference example (self-contained).
+ViTeX-Edit-14B inference example (self-contained).
 
 Assumes you cloned this HuggingFace repo and are running this script from the
 repo root. The bundled `diffsynth/` library, `vitex_14b.safetensors` weights,
@@ -119,7 +119,7 @@ def build_pipeline(device="cuda:0"):
         redirect_common_files=False,
     )
 
-    print(f"Loading ViTeX-14B trained weights from {ADAPTER_CKPT}")
+    print(f"Loading ViTeX-Edit-14B trained weights from {ADAPTER_CKPT}")
     state = load_state_dict(ADAPTER_CKPT)
     res = pipe.vace.load_state_dict(state, strict=False)
     print(f"  loaded {len(state)} keys (missing {len(res.missing_keys)}, unexpected {len(res.unexpected_keys)})")

make_corp_baseline.py

@@ -1,7 +1,7 @@
-"""Build the ViTeX-14B (Composite) baseline.
+"""Build the ViTeX-Edit-14B (Composite) baseline.
 
 For each test clip:
-  1. Read source video, ViTeX-14B prediction, and the dilated text mask.
+  1. Read source video, ViTeX-Edit-14B prediction, and the dilated text mask.
   2. Color-correct the prediction inside the mask to match the source by
      Reinhard-style mean+std matching in LAB space, using a 20-px band just
      outside the mask as the reference (so the local lighting is captured).
@@ -148,7 +148,7 @@ def main():
     ap.add_argument("--records", required=True)
     ap.add_argument("--data_root", required=True)
     ap.add_argument("--pred_dir", required=True,
-                    help="Directory of ViTeX-14B raw predictions (e.g., ViTeX-14B_orig)")
+                    help="Directory of ViTeX-Edit-14B raw predictions (e.g., ViTeX-Edit-14B_orig)")
     ap.add_argument("--out_dir", required=True,
                     help="Where the corp baseline mp4s are written")
     ap.add_argument("--target_frames", type=int, default=120)