Fix model card: actual ONNX input names are down_residual_*/mid_residual (not down_block_res_samples_*/mid_block_res_sample)

README.md

@@ -27,8 +27,8 @@ A single fused ONNX FP16 graph combining the SD 1.5 UNet with IP-Adapter image-c
 | `timestep` | `[batch]` | FP16 | scheduler timestep |
 | `encoder_hidden_states` | `[batch, 77, 768]` | FP16 | text embeds (e.g. from CLIP text encoder) |
 | `image_embeds` | `[batch, num_images, 1024]` | FP16 | **rank-3** per diffusers 0.27.2's `MultiIPAdapterImageProjection`. On-device path uses `num_images=1`. |
-| `down_block_res_samples_0..11` | 12 tensors | FP16 | ControlNet down-block residuals (canonical SD 1.5 shapes). Pass zeros for Phase-6-only inference. |
-| `mid_block_res_sample` | `[batch, 1280, 8, 8]` | FP16 | ControlNet mid-block residual. Pass zeros for Phase-6-only inference. |
+| `down_residual_0..11` | 12 tensors | FP16 | ControlNet down-block residuals (canonical SD 1.5 shapes). Pass zeros for Phase-6-only inference. |
+| `mid_residual` | `[batch, 1280, 8, 8]` | FP16 | ControlNet mid-block residual. Pass zeros for Phase-6-only inference. |
 
 | Output | Shape | dtype |
 |---|---|---|