fix: add alpha channel input for Qwen Image 2.1 and relative docs (#2021)

This commit is contained in:
Weiqi Gao authored and GitHub committed 2026-09-22 21:45:06 +08:00
1 parent e01206574b
commit e112ab5a50
12 files changed
+125 -50

No files matched your search

+5 -2
View File
@@ -735,12 +735,15 @@ Any image field accepts:
Channel expectations:
- `init_image`: 3 channels
- `ref_images[]`: 3 channels
- `init_image`: native channels (3 or 4); alpha is preserved and applied per model
- `ref_images[]`: native channels (3 or 4); alpha is preserved and applied per model
- `control_image`: 3 channels
- `ip_adapter_image`: 3 channels
- `mask_image`: 1 channel
Models that support RGBA (e.g. Qwen-Image 2.1) use the alpha channel of `init_image`
and `ref_images[]`. RGB-only models drop it, so sending RGBA is safe for every model.
If omitted or null:
- single-image fields map to an empty `sd_image_t`