self-contained torch wheel

Bundles the known-working ROCm torch, triton-rocm, and torchvision wheels
locally so install no longer depends on the PyTorch nightly index being
available. Also fixes model name mismatches between docs and code, and
adds missing dependencies.

What:

  • wheels/ — bundled torch 2.11.0+rocm7.2, triton-rocm 3.6.0, and
    torchvision 0.26.0+rocm7.2 (wheels/ is in .gitignore; they are
    downloaded once and reused)
  • README install section — replaced 'pip install torch --index-url ...'
    with 'pip install wheels/*.whl' for all three ROCm wheels; added
    download instructions for the initial fetch
  • README Current State — marked self-contained torch wheel as done,
    removed from Future Improvements
  • Fixed model name defaults across README examples and session.py
    docstring — they used shortened filenames (novaAnimeXL.safetensors,
    qwen_image_edit.safetensors) that don't match the actual symlinks
    created by the Models section
  • pyproject.toml — added torchvision and realesrgan (previously
    undeclared; upscale.py imported torchvision.transforms at module
    level without the dependency being declared)

Why:

The ROCm nightly index is volatile — versions rotate frequently and the
index itself may not be reachable. Bundling the three ROCm-only wheels
(torch, triton-rocm, torchvision) makes the install reproducible. All
other dependencies resolve from standard PyPI.

Verified by creating a clean Python 3.12 venv, installing all three
wheels from the local files, running 'pip install -e .', and confirming
'vnasset --help' and GPU tensor allocation work without any remote
ROCm index access.

.gitignore

@@ -6,3 +6,4 @@ models/
 dist/
 build/
 output/
+wheels/

README.md

@@ -26,13 +26,25 @@ cd vnassets
 python3.12 -m venv .venv
 source .venv/bin/activate
 
-# Install ROCm PyTorch (adjust index URL for your ROCm version)
-pip install torch --index-url https://download.pytorch.org/whl/rocm7.2
+# Install ROCm PyTorch from local wheels (no remote index dependency)
+pip install wheels/torch-2.11.0+rocm7.2-cp312-cp312-manylinux_2_28_x86_64.whl \
+            wheels/triton_rocm-3.6.0-cp312-cp312-linux_x86_64.whl \
+            wheels/torchvision-0.26.0+rocm7.2-cp312-cp312-manylinux_2_28_x86_64.whl
 
 # Install the rest
 pip install -e .
 ```
 
+The torch, triton-rocm, and torchvision wheels are bundled in `wheels/`. If
+you don't have them yet (e.g. after a fresh clone), download them first:
+
+```bash
+mkdir -p wheels
+python3.12 -m pip download torch==2.11.0 triton-rocm==3.6.0 torchvision==0.26.0 \
+    --index-url https://download.pytorch.org/whl/rocm7.2 \
+    --dest wheels --no-deps
+```
+
 ### Models
 
 Symlink your ComfyUI models into `models/`:
@@ -74,9 +86,9 @@ Config structure:
 
 ```yaml
 session:
-  sdxl_checkpoint: models/novaAnimeXL.safetensors
-  edit_model: models/qwen_image_edit.safetensors
-  edit_lora: models/lightning-4steps.safetensors  # optional
+  sdxl_checkpoint: models/novaAnimeXL_ilV190.safetensors
+  edit_model: models/qwen_image_edit_2509_fp8_e4m3fn.safetensors
+  edit_lora: models/Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors  # optional
 
 output_dir: output/my_pipeline
 
@@ -221,9 +233,9 @@ memory between operations. Models are loaded eagerly at construction:
 from vnassets import VnAssetsSession
 
 with VnAssetsSession(
-    sdxl_checkpoint="models/novaAnimeXL.safetensors",
-    edit_model="models/qwen_image_edit.safetensors",
-    edit_lora="models/lightning-4steps.safetensors",
+    sdxl_checkpoint="models/novaAnimeXL_ilV190.safetensors",
+    edit_model="models/qwen_image_edit_2509_fp8_e4m3fn.safetensors",
+    edit_lora="models/Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors",
 ) as vna:
     vna.generate("1girl, red hair", output="base.png")
     vna.edit("base.png", "make her smile", output="happy.png")
@@ -572,6 +584,7 @@ Use `--raw` to bypass weighting and fall back to plain diffusers encoding.
 | Flash attention (experimental) | ✅ Working |
 | `vnasset remove-bg` | ✅ Working |
 | `vnasset upscale` | ✅ Working |
+| Self-contained torch wheel | ✅ Working |
 | `vnasset serve` (daemon/HTTP API) | 🚧 Planned |
 | `torch.compile` on UNet | 🚧 Planned |
 | Batch edit loop (shared VAE encode) | 🚧 Planned |
@@ -583,9 +596,5 @@ Use `--raw` to bypass weighting and fall back to plain diffusers encoding.
 - **Shared encode optimization** — for N edit variants of the same input image,
   run VAE encode and VL visual token encoding once, then only text-encode and
   denoise per variant.
-- **Self-contained torch wheel** — bundle the known-working torch wheel file in
-  the project (`wheels/torch-2.11.0+rocm7.2-cp312-cp312-linux_x86_64.whl`) so
-  the install is reproducible without depending on PyTorch's nightly index
-  availability or a ComfyUI installation.
 - **`vnasset serve`** — lightweight daemon with Unix socket or HTTP API for
   integrating VNAsset into external tools.

pyproject.toml

@@ -18,6 +18,8 @@ dependencies = [
     "compel",
     "rembg",
     "onnxruntime",
+    "torchvision",
+    "realesrgan",
 ]
 
 [tool.setuptools.packages.find]

vnassets/session.py

@@ -40,9 +40,9 @@ class VnAssetsSession:
     Usage as context manager::
 
         with VnAssetsSession(
-            sdxl_checkpoint="models/novaAnimeXL.safetensors",
-            edit_model="models/qwen_image_edit.safetensors",
-            edit_lora="models/lightning-4steps.safetensors",
+            sdxl_checkpoint="models/novaAnimeXL_ilV190.safetensors",
+            edit_model="models/qwen_image_edit_2509_fp8_e4m3fn.safetensors",
+            edit_lora="models/Qwen-Image-Edit-2509-Lightning-4steps-V1.0-bf16.safetensors",
         ) as vna:
             vna.generate("1girl, red hair", output="base.png")
             vna.edit("base.png", "make her smile", output="happy.png")