From ffeda47fd221963ce382b969cba5a62958964052 Mon Sep 17 00:00:00 2001
From: kami <kamixtrash@gmail.com>
Date: Tue, 11 Aug 2026 03:28:26 +0400
Subject: [PATCH] Restore runtime deps: models, dots.tts, torchvision shadow

Rebuild the venv half of the reconstruction. Adds the two CPU onnx
detectors back under models/ (comic-text-detector, deepghs anime face,
both gitignored), re-clones the dots.tts checkout, and records both
recipes in requirements.txt so the next rebuild skips the archaeology.

Two pre-existing environment breakages had to be cleared:

- Arch's torchvision 0.25 is too old for torch 2.13, so every
  transformers model import died with "operator torchvision::nms does
  not exist". Shadowed with 0.28.0+rocm7.2 inside the venv only, so the
  system copy stays put.
- dots_tts refuses to import when torch and torchaudio minors differ,
  and that pair is unsatisfiable here: 2.11 is the newest torchaudio
  ROCm wheel there is. Verified 2.11 loads and resamples against 2.13,
  then scoped a bypass around the import in both call sites.

Self-checks 13/14. worker_layers still needs the ComfyUI workflow json,
which legacy/ took with it.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
---
 .gitignore                |  1 +
 requirements.txt          | 13 +++++++++++++
 scripts/pick_tts_voice.py | 13 ++++++++++++-
 worker_tts.py             | 12 +++++++++++-
 4 files changed, 37 insertions(+), 2 deletions(-)

diff --git a/.gitignore b/.gitignore
index 5906d58..3ecd73d 100644
--- a/.gitignore
+++ b/.gitignore
@@ -4,3 +4,4 @@ __pycache__/
 dots.tts/
 /dev/shm/
 *.gguf
+models/
diff --git a/requirements.txt b/requirements.txt
index 39b9212..6ad55fd 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -13,3 +13,16 @@ transformers
 accelerate
 soundfile
 # system deps (not pip): ffmpeg, comfyui (external server)
+#
+# dots.tts (gitignored checkout, needed by worker_tts + scripts/pick_tts_voice). venv is built
+# --system-site-packages so it inherits Arch's rocm torch:
+#   git clone https://github.com/rednote-hilab/dots.tts.git dots.tts
+#   pip install -e ./dots.tts --no-deps --ignore-requires-python   # py3.14 > its <3.13 pin, skips gradio
+#   pip install librosa loguru einops torchdiffeq 'langcodes[data]' lingua-language-detector WeTextProcessing
+#   pip install --no-deps --index-url https://download.pytorch.org/whl/rocm7.2 torchvision==0.28.0+rocm7.2
+# that last one is not optional: Arch's torchvision 0.25 is too old for torch 2.13, and every
+# transformers model import dies with "operator torchvision::nms does not exist" until it is shadowed.
+#
+# models/ (gitignored, CPU onnx for set-of-mark):
+#   comictextdetector.pt.onnx  <- github.com/zyddnys/manga-image-translator releases/beta-0.3
+#   anime_face_v1.4_s.onnx     <- huggingface.co/deepghs/anime_face_detection face_detect_v1.4_s/model.onnx
diff --git a/scripts/pick_tts_voice.py b/scripts/pick_tts_voice.py
index 5027f94..f438fa6 100644
--- a/scripts/pick_tts_voice.py
+++ b/scripts/pick_tts_voice.py
@@ -25,7 +25,18 @@ def load_model(model_name: str):
             cls, *args, **{"fix_mistral_regex": True, **kwargs}
         )
     )
-    from dots_tts.runtime import DotsTtsRuntime
+    # Match worker_tts.py's torch/torchaudio minor-mismatch bypass too.
+    import torch
+    import importlib.metadata as metadata
+
+    real_version = metadata.version
+    metadata.version = (
+        lambda name: torch.__version__ if name == "torchaudio" else real_version(name)
+    )
+    try:
+        from dots_tts.runtime import DotsTtsRuntime
+    finally:
+        metadata.version = real_version
 
     return DotsTtsRuntime.from_pretrained(model_name, precision="bfloat16")
 
diff --git a/worker_tts.py b/worker_tts.py
index 50d5e0d..ad0ff32 100644
--- a/worker_tts.py
+++ b/worker_tts.py
@@ -36,7 +36,17 @@ def _load_tts():
         transformers.AutoTokenizer.from_pretrained = classmethod(
             lambda cls, *a, **kw: _orig(cls, *a, **{"fix_mistral_regex": True, **kw})
         )
-        from dots_tts.runtime import DotsTtsRuntime
+        # dots_tts/__init__.py refuses to import when torch and torchaudio minors differ. workpc runs
+        # Arch's torch 2.13 but pytorch.org ships no torchaudio past 2.11 for ROCm, so the pair can't
+        # be satisfied; 2.11 loads and resamples fine against 2.13. Lie to the guard for the import.
+        # ponytail: drop this once a torchaudio matching torch's minor exists for ROCm.
+        import torch, importlib.metadata as _md
+        _ver = _md.version
+        _md.version = lambda n: torch.__version__ if n == "torchaudio" else _ver(n)
+        try:
+            from dots_tts.runtime import DotsTtsRuntime
+        finally:
+            _md.version = _ver
         _tts = DotsTtsRuntime.from_pretrained(DOTS_MODEL, precision="bfloat16")
     return _tts