Support qwen inpaint controlnet. (Comfy-Org#9772)

Author: comfyanonymous

comfy/controlnet.py

@@ -253,7 +253,10 @@ def get_control(self, x_noisy, t, cond, batched_number, transformer_options):
                 to_concat = []
                 for c in self.extra_concat_orig:
                     c = c.to(self.cond_hint.device)
-                    c = comfy.utils.common_upscale(c, self.cond_hint.shape[3], self.cond_hint.shape[2], self.upscale_algorithm, "center")
+                    c = comfy.utils.common_upscale(c, self.cond_hint.shape[-1], self.cond_hint.shape[-2], self.upscale_algorithm, "center")
+                    if c.ndim < self.cond_hint.ndim:
+                        c = c.unsqueeze(2)
+                        c = comfy.utils.repeat_to_batch_size(c, self.cond_hint.shape[2], dim=2)
                     to_concat.append(comfy.utils.repeat_to_batch_size(c, self.cond_hint.shape[0]))
                 self.cond_hint = torch.cat([self.cond_hint] + to_concat, dim=1)
 
@@ -585,11 +588,18 @@ def load_controlnet_flux_instantx(sd, model_options={}):
 
 def load_controlnet_qwen_instantx(sd, model_options={}):
     model_config, operations, load_device, unet_dtype, manual_cast_dtype, offload_device = controlnet_config(sd, model_options=model_options)
-    control_model = comfy.ldm.qwen_image.controlnet.QwenImageControlNetModel(operations=operations, device=offload_device, dtype=unet_dtype, **model_config.unet_config)
+    control_latent_channels = sd.get("controlnet_x_embedder.weight").shape[1]
+
+    extra_condition_channels = 0
+    concat_mask = False
+    if control_latent_channels == 68: #inpaint controlnet
+        extra_condition_channels = control_latent_channels - 64
+        concat_mask = True
+    control_model = comfy.ldm.qwen_image.controlnet.QwenImageControlNetModel(extra_condition_channels=extra_condition_channels, operations=operations, device=offload_device, dtype=unet_dtype, **model_config.unet_config)
     control_model = controlnet_load_state_dict(control_model, sd)
     latent_format = comfy.latent_formats.Wan21()
     extra_conds = []
-    control = ControlNet(control_model, compression_ratio=1, latent_format=latent_format, load_device=load_device, manual_cast_dtype=manual_cast_dtype, extra_conds=extra_conds)
+    control = ControlNet(control_model, compression_ratio=1, latent_format=latent_format, concat_mask=concat_mask, load_device=load_device, manual_cast_dtype=manual_cast_dtype, extra_conds=extra_conds)
     return control
 
 def convert_mistoline(sd):