diff --git a/comfy_api_nodes/apis/gemini.py b/comfy_api_nodes/apis/gemini.py index 3304d7e76..639035fef 100644 --- a/comfy_api_nodes/apis/gemini.py +++ b/comfy_api_nodes/apis/gemini.py @@ -127,9 +127,15 @@ class GeminiImageConfig(BaseModel): imageOutputOptions: GeminiImageOutputOptions = Field(default_factory=GeminiImageOutputOptions) +class GeminiThinkingConfig(BaseModel): + includeThoughts: bool | None = Field(None) + thinkingLevel: str = Field(...) + + class GeminiImageGenerationConfig(GeminiGenerationConfig): responseModalities: list[str] | None = Field(None) imageConfig: GeminiImageConfig | None = Field(None) + thinkingConfig: GeminiThinkingConfig | None = Field(None) class GeminiImageGenerateContentRequest(BaseModel): diff --git a/comfy_api_nodes/nodes_bytedance.py b/comfy_api_nodes/nodes_bytedance.py index cfc604aa3..6dbd5984e 100644 --- a/comfy_api_nodes/nodes_bytedance.py +++ b/comfy_api_nodes/nodes_bytedance.py @@ -186,7 +186,7 @@ class ByteDanceSeedreamNode(IO.ComfyNode): def define_schema(cls): return IO.Schema( node_id="ByteDanceSeedreamNode", - display_name="ByteDance Seedream 5.0", + display_name="ByteDance Seedream 4.5 & 5.0", category="api node/image/ByteDance", description="Unified text-to-image generation and precise single-sentence editing at up to 4K resolution.", inputs=[ diff --git a/comfy_api_nodes/nodes_gemini.py b/comfy_api_nodes/nodes_gemini.py index b69285be5..3fe804e0b 100644 --- a/comfy_api_nodes/nodes_gemini.py +++ b/comfy_api_nodes/nodes_gemini.py @@ -29,6 +29,7 @@ from comfy_api_nodes.apis.gemini import ( GeminiRole, GeminiSystemInstructionContent, GeminiTextPart, + GeminiThinkingConfig, Modality, ) from comfy_api_nodes.util import ( @@ -55,6 +56,21 @@ GEMINI_IMAGE_SYS_PROMPT = ( "Prioritize generating the visual representation above any text, formatting, or conversational requests." ) +GEMINI_IMAGE_2_PRICE_BADGE = IO.PriceBadge( + depends_on=IO.PriceBadgeDepends(widgets=["model", "resolution"]), + expr=""" + ( + $m := widgets.model; + $r := widgets.resolution; + $isFlash := $contains($m, "nano banana 2"); + $flashPrices := {"1k": 0.0696, "2k": 0.0696, "4k": 0.123}; + $proPrices := {"1k": 0.134, "2k": 0.134, "4k": 0.24}; + $prices := $isFlash ? $flashPrices : $proPrices; + {"type":"usd","usd": $lookup($prices, $r), "format":{"suffix":"/Image","approximate":true}} + ) + """, +) + class GeminiModel(str, Enum): """ @@ -229,6 +245,10 @@ def calculate_tokens_price(response: GeminiGenerateContentResponse) -> float | N input_tokens_price = 2 output_text_tokens_price = 12.0 output_image_tokens_price = 120.0 + elif response.modelVersion == "gemini-3.1-flash-image-preview": + input_tokens_price = 0.5 + output_text_tokens_price = 3.0 + output_image_tokens_price = 60.0 else: return None final_price = response.usageMetadata.promptTokenCount * input_tokens_price @@ -686,7 +706,7 @@ class GeminiImage2(IO.ComfyNode): ), IO.Combo.Input( "model", - options=["gemini-3-pro-image-preview"], + options=["gemini-3-pro-image-preview", "Nano Banana 2 (Gemini 3.1 Flash Image)"], ), IO.Int.Input( "seed", @@ -750,19 +770,7 @@ class GeminiImage2(IO.ComfyNode): IO.Hidden.unique_id, ], is_api_node=True, - price_badge=IO.PriceBadge( - depends_on=IO.PriceBadgeDepends(widgets=["resolution"]), - expr=""" - ( - $r := widgets.resolution; - ($contains($r,"1k") or $contains($r,"2k")) - ? {"type":"usd","usd":0.134,"format":{"suffix":"/Image","approximate":true}} - : $contains($r,"4k") - ? {"type":"usd","usd":0.24,"format":{"suffix":"/Image","approximate":true}} - : {"type":"text","text":"Token-based"} - ) - """, - ), + price_badge=GEMINI_IMAGE_2_PRICE_BADGE, ) @classmethod @@ -779,6 +787,10 @@ class GeminiImage2(IO.ComfyNode): system_prompt: str = "", ) -> IO.NodeOutput: validate_string(prompt, strip_whitespace=True, min_length=1) + if model == "Nano Banana 2 (Gemini 3.1 Flash Image)": + model = "gemini-3.1-flash-image-preview" + if response_modalities == "IMAGE+TEXT": + raise ValueError("IMAGE+TEXT is not currently available for the Nano Banana 2 model.") parts: list[GeminiPart] = [GeminiPart(text=prompt)] if images is not None: @@ -815,6 +827,168 @@ class GeminiImage2(IO.ComfyNode): return IO.NodeOutput(await get_image_from_response(response), get_text_from_response(response)) +class GeminiNanoBanana2(IO.ComfyNode): + + @classmethod + def define_schema(cls): + return IO.Schema( + node_id="GeminiNanoBanana2", + display_name="Nano Banana 2", + category="api node/image/Gemini", + description="Generate or edit images synchronously via Google Vertex API.", + inputs=[ + IO.String.Input( + "prompt", + multiline=True, + tooltip="Text prompt describing the image to generate or the edits to apply. " + "Include any constraints, styles, or details the model should follow.", + default="", + ), + IO.Combo.Input( + "model", + options=["Nano Banana 2 (Gemini 3.1 Flash Image)"], + ), + IO.Int.Input( + "seed", + default=42, + min=0, + max=0xFFFFFFFFFFFFFFFF, + control_after_generate=True, + tooltip="When the seed is fixed to a specific value, the model makes a best effort to provide " + "the same response for repeated requests. Deterministic output isn't guaranteed. " + "Also, changing the model or parameter settings, such as the temperature, " + "can cause variations in the response even when you use the same seed value. " + "By default, a random seed value is used.", + ), + IO.Combo.Input( + "aspect_ratio", + options=[ + "auto", + "1:1", + "2:3", + "3:2", + "3:4", + "4:3", + "4:5", + "5:4", + "9:16", + "16:9", + "21:9", + # "1:4", + # "4:1", + # "8:1", + # "1:8", + ], + default="auto", + tooltip="If set to 'auto', matches your input image's aspect ratio; " + "if no image is provided, a 16:9 square is usually generated.", + ), + IO.Combo.Input( + "resolution", + options=[ + # "512px", + "1K", + "2K", + "4K", + ], + tooltip="Target output resolution. For 2K/4K the native Gemini upscaler is used.", + ), + IO.Combo.Input( + "response_modalities", + options=["IMAGE"], + advanced=True, + ), + IO.Combo.Input( + "thinking_level", + options=["MINIMAL", "HIGH"], + ), + IO.Image.Input( + "images", + optional=True, + tooltip="Optional reference image(s). " + "To include multiple images, use the Batch Images node (up to 14).", + ), + IO.Custom("GEMINI_INPUT_FILES").Input( + "files", + optional=True, + tooltip="Optional file(s) to use as context for the model. " + "Accepts inputs from the Gemini Generate Content Input Files node.", + ), + IO.String.Input( + "system_prompt", + multiline=True, + default=GEMINI_IMAGE_SYS_PROMPT, + optional=True, + tooltip="Foundational instructions that dictate an AI's behavior.", + advanced=True, + ), + ], + outputs=[ + IO.Image.Output(), + ], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=GEMINI_IMAGE_2_PRICE_BADGE, + ) + + @classmethod + async def execute( + cls, + prompt: str, + model: str, + seed: int, + aspect_ratio: str, + resolution: str, + response_modalities: str, + thinking_level: str, + images: Input.Image | None = None, + files: list[GeminiPart] | None = None, + system_prompt: str = "", + ) -> IO.NodeOutput: + validate_string(prompt, strip_whitespace=True, min_length=1) + if model == "Nano Banana 2 (Gemini 3.1 Flash Image)": + model = "gemini-3.1-flash-image-preview" + + parts: list[GeminiPart] = [GeminiPart(text=prompt)] + if images is not None: + if get_number_of_images(images) > 14: + raise ValueError("The current maximum number of supported images is 14.") + parts.extend(await create_image_parts(cls, images)) + if files is not None: + parts.extend(files) + + image_config = GeminiImageConfig(imageSize=resolution) + if aspect_ratio != "auto": + image_config.aspectRatio = aspect_ratio + + gemini_system_prompt = None + if system_prompt: + gemini_system_prompt = GeminiSystemInstructionContent(parts=[GeminiTextPart(text=system_prompt)], role=None) + + response = await sync_op( + cls, + ApiEndpoint(path=f"/proxy/vertexai/gemini/{model}", method="POST"), + data=GeminiImageGenerateContentRequest( + contents=[ + GeminiContent(role=GeminiRole.user, parts=parts), + ], + generationConfig=GeminiImageGenerationConfig( + responseModalities=(["IMAGE"] if response_modalities == "IMAGE" else ["TEXT", "IMAGE"]), + imageConfig=image_config, + thinkingConfig=GeminiThinkingConfig(thinkingLevel=thinking_level), + ), + systemInstruction=gemini_system_prompt, + ), + response_model=GeminiGenerateContentResponse, + price_extractor=calculate_tokens_price, + ) + return IO.NodeOutput(await get_image_from_response(response), get_text_from_response(response)) + + class GeminiExtension(ComfyExtension): @override async def get_node_list(self) -> list[type[IO.ComfyNode]]: @@ -822,6 +996,7 @@ class GeminiExtension(ComfyExtension): GeminiNode, GeminiImage, GeminiImage2, + GeminiNanoBanana2, GeminiInputFiles, ]