Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

feat(GeminiImage-ApiNode): add aspect_ratio and release version of model (#10255)

Alexander Piskunaa895db7e876
diff --git a/comfy_api_nodes/apis/gemini_api.py b/comfy_api_nodes/apis/gemini_api.py
index 138bf035d..2bf28bf93 100644
--- a/comfy_api_nodes/apis/gemini_api.py
+++ b/comfy_api_nodes/apis/gemini_api.py
@@ -1,19 +1,22 @@
-from __future__ import annotations
-
-from typing import List, Optional
+from typing import Optional
from comfy_api_nodes.apis import GeminiGenerationConfig, GeminiContent, GeminiSafetySetting, GeminiSystemInstructionContent, GeminiTool, GeminiVideoMetadata
from pydantic import BaseModel
+class GeminiImageConfig(BaseModel):
+ aspectRatio: Optional[str] = None
+
+
class GeminiImageGenerationConfig(GeminiGenerationConfig):
- responseModalities: Optional[List[str]] = None
+ responseModalities: Optional[list[str]] = None
+ imageConfig: Optional[GeminiImageConfig] = None
class GeminiImageGenerateContentRequest(BaseModel):
- contents: List[GeminiContent]
+ contents: list[GeminiContent]
generationConfig: Optional[GeminiImageGenerationConfig] = None
- safetySettings: Optional[List[GeminiSafetySetting]] = None
+ safetySettings: Optional[list[GeminiSafetySetting]] = None
systemInstruction: Optional[GeminiSystemInstructionContent] = None
- tools: Optional[List[GeminiTool]] = None
+ tools: Optional[list[GeminiTool]] = None
videoMetadata: Optional[GeminiVideoMetadata] = None
diff --git a/comfy_api_nodes/nodes_gemini.py b/comfy_api_nodes/nodes_gemini.py
index 309e9a2d2..c1941cbe9 100644
--- a/comfy_api_nodes/nodes_gemini.py
+++ b/comfy_api_nodes/nodes_gemini.py
@@ -26,7 +26,7 @@ from comfy_api_nodes.apis import (
GeminiPart,
GeminiMimeType,
)
-from comfy_api_nodes.apis.gemini_api import GeminiImageGenerationConfig, GeminiImageGenerateContentRequest
+from comfy_api_nodes.apis.gemini_api import GeminiImageGenerationConfig, GeminiImageGenerateContentRequest, GeminiImageConfig
from comfy_api_nodes.apis.client import (
ApiEndpoint,
HttpMethod,
@@ -63,6 +63,7 @@ class GeminiImageModel(str, Enum):
"""
gemini_2_5_flash_image_preview = "gemini-2.5-flash-image-preview"
+ gemini_2_5_flash_image = "gemini-2.5-flash-image"
def get_gemini_endpoint(
@@ -538,7 +539,7 @@ class GeminiImage(ComfyNodeABC):
{
"tooltip": "The Gemini model to use for generating responses.",
"options": [model.value for model in GeminiImageModel],
- "default": GeminiImageModel.gemini_2_5_flash_image_preview.value,
+ "default": GeminiImageModel.gemini_2_5_flash_image.value,
},
),
"seed": (
@@ -579,6 +580,14 @@ class GeminiImage(ComfyNodeABC):
# "tooltip": "How many images to generate",
# },
# ),
+ "aspect_ratio": (
+ IO.COMBO,
+ {
+ "tooltip": "Defaults to matching the output image size to that of your input image, or otherwise generates 1:1 squares.",
+ "options": ["auto", "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9"],
+ "default": "auto",
+ },
+ ),
},
"hidden": {
"auth_token": "AUTH_TOKEN_COMFY_ORG",
@@ -600,15 +609,17 @@ class GeminiImage(ComfyNodeABC):
images: Optional[IO.IMAGE] = None,
files: Optional[list[GeminiPart]] = None,
n=1,
+ aspect_ratio: str = "auto",
unique_id: Optional[str] = None,
**kwargs,
):
- # Validate inputs
validate_string(prompt, strip_whitespace=True, min_length=1)
- # Create parts list with text prompt as the first part
parts: list[GeminiPart] = [create_text_part(prompt)]
- # Add other modal parts
+ if not aspect_ratio:
+ aspect_ratio = "auto" # for backward compatability with old workflows; to-do remove this in December
+ image_config = GeminiImageConfig(aspectRatio=aspect_ratio)
+
if images is not None:
image_parts = create_image_parts(images)
parts.extend(image_parts)
@@ -625,7 +636,8 @@ class GeminiImage(ComfyNodeABC):
),
],
generationConfig=GeminiImageGenerationConfig(
- responseModalities=["TEXT","IMAGE"]
+ responseModalities=["TEXT","IMAGE"],
+ imageConfig=None if aspect_ratio == "auto" else image_config,
)
),
auth_kwargs=kwargs,