Merge af96939c95 into e4b4fb3479

Needed to load the proper LTX2 VAE if separated from checkpoint

comfy_api/latest/_input_impl/video_types.py

@@ -374,7 +374,7 @@ class VideoFromComponents(VideoInput):
             if audio_stream and self.__components.audio:
                 waveform = self.__components.audio['waveform']
                 waveform = waveform[:, :, :math.ceil((audio_sample_rate / frame_rate) * self.__components.images.shape[0])]
-                frame = av.AudioFrame.from_ndarray(waveform.movedim(2, 1).reshape(1, -1).float().numpy(), format='flt', layout='mono' if waveform.shape[1] == 1 else 'stereo')
+                frame = av.AudioFrame.from_ndarray(waveform.movedim(2, 1).reshape(1, -1).float().cpu().numpy(), format='flt', layout='mono' if waveform.shape[1] == 1 else 'stereo')
                 frame.sample_rate = audio_sample_rate
                 frame.pts = 0
                 output.mux(audio_stream.encode(frame))

comfy_api_nodes/nodes_gemini.py

@@ -130,7 +130,7 @@ def get_parts_by_type(response: GeminiGenerateContentResponse, part_type: Litera
     Returns:
         List of response parts matching the requested type.
     """
-    if response.candidates is None:
+    if not response.candidates:
         if response.promptFeedback and response.promptFeedback.blockReason:
             feedback = response.promptFeedback
             raise ValueError(
@@ -141,14 +141,24 @@ def get_parts_by_type(response: GeminiGenerateContentResponse, part_type: Litera
             "try changing it to `IMAGE+TEXT` to view the model's reasoning and understand why image generation failed."
         )
     parts = []
-    for part in response.candidates[0].content.parts:
-        if part_type == "text" and part.text:
-            parts.append(part)
-        elif part.inlineData and part.inlineData.mimeType == part_type:
-            parts.append(part)
-        elif part.fileData and part.fileData.mimeType == part_type:
-            parts.append(part)
-        # Skip parts that don't match the requested type
+    blocked_reasons = []
+    for candidate in response.candidates:
+        if candidate.finishReason and candidate.finishReason.upper() == "IMAGE_PROHIBITED_CONTENT":
+            blocked_reasons.append(candidate.finishReason)
+            continue
+        if candidate.content is None or candidate.content.parts is None:
+            continue
+        for part in candidate.content.parts:
+            if part_type == "text" and part.text:
+                parts.append(part)
+            elif part.inlineData and part.inlineData.mimeType == part_type:
+                parts.append(part)
+            elif part.fileData and part.fileData.mimeType == part_type:
+                parts.append(part)
+
+    if not parts and blocked_reasons:
+        raise ValueError(f"Gemini API blocked the request. Reasons: {blocked_reasons}")
+
     return parts
 
 

comfy_extras/nodes_model_patch.py

@@ -244,6 +244,10 @@ class ModelPatchLoader:
         elif 'control_all_x_embedder.2-1.weight' in sd: # alipai z image fun controlnet
             sd = z_image_convert(sd)
             config = {}
+            if 'control_layers.4.adaLN_modulation.0.weight' not in sd:
+                config['n_control_layers'] = 3
+                config['additional_in_dim'] = 17
+                config['refiner_control'] = True
             if 'control_layers.14.adaLN_modulation.0.weight' in sd:
                 config['n_control_layers'] = 15
                 config['additional_in_dim'] = 17

nodes.py

@@ -798,8 +798,8 @@ class VAELoader:
                 vae_path = folder_paths.get_full_path_or_raise("vae_approx", vae_name)
             else:
                 vae_path = folder_paths.get_full_path_or_raise("vae", vae_name)
-            sd = comfy.utils.load_torch_file(vae_path)
-        vae = comfy.sd.VAE(sd=sd)
+            sd, metadata = comfy.utils.load_torch_file(vae_path, return_metadata=True)
+        vae = comfy.sd.VAE(sd=sd, metadata=metadata)
         vae.throw_exception_if_invalid()
         return (vae,)