Release 0.37.1 with the Chroma tokenizer dependency

docs/installation.md

@@ -77,9 +77,11 @@ uv tool install --force "remove-ai-watermarks[qwen-zimage]"
 Both remaining profiles run a Z-Image face stage on the DiffSynth runtime, so
 both need this extra. The third profile, `chroma-zimage`, uses diffusers'
 ChromaImg2ImgPipeline instead of DiffSynth for its global stage but inherits
-the same face stage, so it needs this extra too. It includes the `diffusion`
-dependencies; `diffusion` on its own covers the torch and diffusers imports
-but not the face stage, so it is not enough to run a removal.
+the same face stage, so it needs this extra too. The extra also installs
+SentencePiece for Chroma1-HD's binary `spiece.model`; without that backend,
+Transformers cannot construct the Chroma tokenizer. It includes the `diffusion`
+dependencies; `diffusion` on its own covers the torch and diffusers imports but
+not the face stage or Chroma tokenizer, so it is not enough to run a removal.
 
 **An NVIDIA GPU is required.** `qwen-zimage`, `sdxl-zimage` and `chroma-zimage`
 are CUDA-only, and
@@ -117,7 +119,7 @@ application actually uses:
 | `diffusion` | Torch and Diffusers runtime; video SynthID regeneration | `pixels`, Torch, Diffusers | Yes |
 | `migan` | MI-GAN ONNX fill backend | `visible`, ONNX Runtime | Model download, no Torch |
 | `lama` | big-LaMa ONNX fill backend | `visible`, ONNX Runtime | Model download, no Torch |
-| `qwen-zimage` | Invisible image-watermark removal, all CUDA-only profiles | `diffusion`, DiffSynth | Yes |
+| `qwen-zimage` | Invisible image-watermark removal, all CUDA-only profiles | `diffusion`, DiffSynth, SentencePiece | Yes |
 | `text-restoration` | Opt-in verified profile-VAE glyph restoration | `qwen-zimage`, `lama` | Yes |
 | `text-draft` | Draft OCR proposals for operator verification | PaddleOCR, PaddlePaddle | Model download, no Torch |
 | `all` | Every production feature available on the active Python | All compatible rows above | Yes |

pyproject.toml

@@ -4,7 +4,7 @@
 # on it, including the ComfyUI node package. The console script below carries
 # the same weight, since users have it on PATH.
 name = "remove-ai-watermarks"
-version = "0.37.0"
+version = "0.37.1"
 description = "AI watermark remover for visible, invisible, and provenance marks in images and video"
 readme = "README.md"
 requires-python = ">=3.11,<3.15"
@@ -118,6 +118,9 @@ diffusion = [
 qwen-zimage = [
     "remove-ai-watermarks[diffusion]",
     "diffsynth>=2.0.17,<3",
+    # Chroma1-HD ships a binary spiece.model. Without the matching backend,
+    # Transformers falls through to tiktoken, which cannot parse that file.
+    "sentencepiece>=0.2.2,<0.3",
     "torchvision>=0.20.0",
 ]
 # Opt-in verified-text reconstruction over qwen-zimage. LaMa removes the changed

src/remove_ai_watermarks/__init__.py

@@ -33,7 +33,7 @@ _os.environ.setdefault("TRANSFORMERS_VERBOSITY", "error")
 _warnings.filterwarnings("ignore", message=r".*ImageProcessorFast.*")
 
 
-__version__ = "0.37.0"
+__version__ = "0.37.1"
 
 __all__ = [
     "BatchSummary",

tests/test_packaging.py

@@ -81,6 +81,10 @@ def test_classify_extra_owns_the_photo_heads() -> None:
     assert {"torch", "transformers", "huggingface-hub", "tokenizers"} <= names
 
 
+def test_qwen_zimage_extra_owns_every_profile_tokenizer_backend() -> None:
+    assert "sentencepiece" in _requirement_names("qwen-zimage")
+
+
 def test_production_all_does_not_include_development_tools():
     assert {
         "pyright",

uv.lock

@@ -3311,7 +3311,7 @@ wheels = [
 
 [[package]]
 name = "remove-ai-watermarks"
-version = "0.37.0"
+version = "0.37.1"
 source = { editable = "." }
 dependencies = [
     { name = "c2pa-python" },
@@ -3336,6 +3336,7 @@ all = [
     { name = "pillow-heif" },
     { name = "pywavelets" },
     { name = "safetensors" },
+    { name = "sentencepiece" },
     { name = "tokenizers" },
     { name = "torch" },
     { name = "torchvision" },
@@ -3412,6 +3413,7 @@ qwen-zimage = [
     { name = "numpy", version = "2.3.5", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.13'" },
     { name = "opencv-python-headless" },
     { name = "safetensors" },
+    { name = "sentencepiece" },
     { name = "tokenizers" },
     { name = "torch" },
     { name = "torchvision" },
@@ -3432,6 +3434,7 @@ text-restoration = [
     { name = "onnxruntime" },
     { name = "opencv-python-headless" },
     { name = "safetensors" },
+    { name = "sentencepiece" },
     { name = "tokenizers" },
     { name = "torch" },
     { name = "torchvision" },
@@ -3500,6 +3503,7 @@ requires-dist = [
     { name = "remove-ai-watermarks", extras = ["visible"], marker = "extra == 'video'" },
     { name = "ruff", marker = "extra == 'dev'", specifier = ">=0.4.0" },
     { name = "safetensors", marker = "extra == 'diffusion'" },
+    { name = "sentencepiece", marker = "extra == 'qwen-zimage'", specifier = ">=0.2.2,<0.3" },
     { name = "tokenizers", marker = "extra == 'classify'", specifier = ">=0.22,<0.23" },
     { name = "tokenizers", marker = "extra == 'diffusion'", specifier = ">=0.22,<0.23" },
     { name = "torch", marker = "extra == 'classify'", specifier = ">=2.0.0" },