Merge branch 'master' into feature/has-intermediate-output

comfy/model_base.py

@@ -890,7 +890,7 @@ class Flux(BaseModel):
         return torch.cat((image, mask), dim=1)
 
     def encode_adm(self, **kwargs):
-        return kwargs["pooled_output"]
+        return kwargs.get("pooled_output", None)
 
     def extra_conds(self, **kwargs):
         out = super().extra_conds(**kwargs)

comfy_api_nodes/nodes_gemini.py

@@ -201,6 +201,16 @@ async def get_image_from_response(response: GeminiGenerateContentResponse, thoug
             returned_image = await download_url_to_image_tensor(part.fileData.fileUri)
         image_tensors.append(returned_image)
     if len(image_tensors) == 0:
+        if not thought:
+            # No images generated --> extract text response for a meaningful error
+            model_message = get_text_from_response(response).strip()
+            if model_message:
+                raise ValueError(f"Gemini did not generate an image. Model response: {model_message}")
+            raise ValueError(
+                "Gemini did not generate an image. "
+                "Try rephrasing your prompt or changing the response modality to 'IMAGE+TEXT' "
+                "to see the model's reasoning."
+            )
         return torch.zeros((1, 1024, 1024, 4))
     return torch.cat(image_tensors, dim=0)
 

comfy_extras/nodes_post_processing.py

@@ -67,11 +67,11 @@ class Blend(io.ComfyNode):
     def g(cls, x):
         return torch.where(x <= 0.25, ((16 * x - 12) * x + 4) * x, torch.sqrt(x))
 
-def gaussian_kernel(kernel_size: int, sigma: float, device=None):
+def gaussian_kernel(kernel_size: int, sigma: float, device=None, dtype=torch.float32):
     x, y = torch.meshgrid(torch.linspace(-1, 1, kernel_size, device=device), torch.linspace(-1, 1, kernel_size, device=device), indexing="ij")
     d = torch.sqrt(x * x + y * y)
     g = torch.exp(-(d * d) / (2.0 * sigma * sigma))
-    return g / g.sum()
+    return (g / g.sum()).to(dtype)
 
 class Blur(io.ComfyNode):
     @classmethod
@@ -99,7 +99,7 @@ class Blur(io.ComfyNode):
         batch_size, height, width, channels = image.shape
 
         kernel_size = blur_radius * 2 + 1
-        kernel = gaussian_kernel(kernel_size, sigma, device=image.device).repeat(channels, 1, 1).unsqueeze(1)
+        kernel = gaussian_kernel(kernel_size, sigma, device=image.device, dtype=image.dtype).repeat(channels, 1, 1).unsqueeze(1)
 
         image = image.permute(0, 3, 1, 2) # Torch wants (B, C, H, W) we use (B, H, W, C)
         padded_image = F.pad(image, (blur_radius,blur_radius,blur_radius,blur_radius), 'reflect')
@@ -200,7 +200,7 @@ class Sharpen(io.ComfyNode):
         image = image.to(comfy.model_management.get_torch_device())
 
         kernel_size = sharpen_radius * 2 + 1
-        kernel = gaussian_kernel(kernel_size, sigma, device=image.device) * -(alpha*10)
+        kernel = gaussian_kernel(kernel_size, sigma, device=image.device, dtype=image.dtype) * -(alpha*10)
         kernel = kernel.to(dtype=image.dtype)
         center = kernel_size // 2
         kernel[center, center] = kernel[center, center] - kernel.sum() + 1.0

requirements.txt

@@ -1,5 +1,5 @@
 comfyui-frontend-package==1.42.8
-comfyui-workflow-templates==0.9.38
+comfyui-workflow-templates==0.9.39
 comfyui-embedded-docs==0.4.3
 torch
 torchsde

utils/mime_types.py

@@ -24,6 +24,7 @@ def init_mime_types():
     # Web types (used by server.py for static file serving)
     mimetypes.add_type('application/javascript; charset=utf-8', '.js')
     mimetypes.add_type('image/webp', '.webp')
+    mimetypes.add_type('image/svg+xml', '.svg')
 
     # Model and data file types (used by asset scanning / metadata extraction)
     mimetypes.add_type("application/safetensors", ".safetensors")