Fix the editing convention: the FIRST image is the target, not the last

The tag/build order in the usage example was inverted, which made swaps silently fail: the model
edits <image1>, so passing the reference first asks it to edit the reference. Verified on one pair
both ways (identity transfers only with the target first); the two edit examples in media/ are
regenerated with the correct order.

README.md

@@ -57,7 +57,8 @@ Every image below is generated by this pipeline with 30 steps at 1024 px.
 
 ![edit single](media/edit_single.jpg)
 
-**Edit — two condition images** (character replacement: identity from `<image1>`, pose/clothing/scene from `<image2>`)
+**Edit — two condition images** (character replacement: `<image1>` is the edit target and keeps its
+pose, clothing and scene; the identity is copied from `<image2>`)
 
 | | |
 |---|---|
@@ -86,14 +87,21 @@ image = pipe(prompt="a red fox in a snowy forest at dusk, cinematic, 85mm",
              output_resolution=1024, num_inference_steps=30,
              generator=torch.Generator("cuda").manual_seed(1234)).images[0]
 
-# editing: 1..N condition images, referenced in the prompt by TAG <image1>, <image2>, ...
-image = pipe(prompt="Replace the woman in <image2> with the woman from <image1>; keep <image2> pose, "
+# editing: 1..N condition images. The FIRST one is the edit target, the rest are references;
+# reference them in the prompt by TAG <image1>, <image2>, ...
+image = pipe(prompt="Replace the woman in <image1> with the woman from <image2>; keep <image1> pose, "
                     "clothing and background unchanged.",
-             image=[ref_image, scene_image],
+             image=[scene_image, ref_image],
              output_resolution=1024, num_inference_steps=30,
              generator=torch.Generator("cuda").manual_seed(1234)).images[0]
 ```
 
+Editing convention: the **first** image is the one being edited (`<image1>`), everything after it is a
+reference. That is the model's own convention and what the stock ComfyUI node documents; feeding the
+reference first is the usual reason a swap "does not happen" (the model then edits the reference).
+Note that the *canvas size* still comes from the last image's aspect ratio — pass `height`/`width`
+explicitly to pin it.
+
 `custom_pipeline="pipeline"` builds the shipped `pipeline.py` and `trust_remote_code=True` lets it run,
 so no clone is needed. (`_class_name` is kept a plain string in `model_index.json` because that is what
 Hub tooling expects; the `[file, class]` form diffusers also accepts makes the Hub print a

example.py

@@ -7,9 +7,10 @@ On the GPU: Qwen3.5-0.8B (~1.7 GB), the DiT with the adapter inside (~14.5 GB) a
   # text-to-image
   python example.py --prompt "a red fox in a snowy forest at dusk, cinematic, 85mm" --out fox.png
 
-  # editing: 1..N condition images, referenced in the prompt by TAG <image1>, <image2>, ...
-  python example.py --image ref.png scene.png \
-      --prompt "Replace the woman in <image2> with the woman from <image1>; keep <image2> pose, \\
+  # editing: 1..N condition images. The FIRST one is the edit target, the rest are references;
+  # the prompt refers to them as <image1>, <image2>, ...
+  python example.py --image scene.png ref.png \
+      --prompt "Replace the woman in <image1> with the woman from <image2>; keep <image1> pose, \\
 clothing and background unchanged." --out swap.png
 
   # a batch from a text file: one prompt per line, '#' starts a comment, blank lines are skipped