From 1c59659a2f448a6eaf8bb9dbc0032ea0d84e7c35 Mon Sep 17 00:00:00 2001 From: Matt Miller Date: Tue, 30 Jun 2026 14:13:20 -0700 Subject: [PATCH 1/2] feat: make asset hashing opt-in via --enable-asset-hashing, off by default (#14663) Add a --enable-asset-hashing CLI flag (action=store_true, default False) and plumb it into the two asset-seeder call sites in main.py that previously hardcoded compute_hashes=True (the startup scan and the post-job output enqueue). Local runs now skip blake3 hashing unless the user opts in, avoiding the startup/per-output cost on large models directories while keeping hashing available for asset-portability features. Co-authored-by: Alexis Rolland --- comfy/cli_args.py | 1 + main.py | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/comfy/cli_args.py b/comfy/cli_args.py index e3099a230..4bef096fb 100644 --- a/comfy/cli_args.py +++ b/comfy/cli_args.py @@ -240,6 +240,7 @@ database_default_path = os.path.abspath( ) parser.add_argument("--database-url", type=str, default=f"sqlite:///{database_default_path}", help="Specify the database URL, e.g. for an in-memory database you can use 'sqlite:///:memory:'.") parser.add_argument("--enable-assets", action="store_true", help="Enable the assets system (API routes, database synchronization, and background scanning).") +parser.add_argument("--enable-asset-hashing", action="store_true", help="Compute blake3 content hashes when scanning assets. Hashing enables future asset-portability features (deduplication, cross-machine model resolution) but adds startup cost and per-output cost on large models directories. Off by default; enable to opt in.") parser.add_argument("--feature-flag", type=str, action='append', default=[], metavar="KEY[=VALUE]", help="Set a server feature flag. Use KEY=VALUE to set an explicit value, or bare KEY to set it to true. Can be specified multiple times. Boolean values (true/false) and numbers are auto-converted. Examples: --feature-flag show_signin_button=true or --feature-flag show_signin_button") parser.add_argument("--list-feature-flags", action="store_true", help="Print the registry of known CLI-settable feature flags as JSON and exit.") diff --git a/main.py b/main.py index aa4ee2adb..20ec83c9e 100644 --- a/main.py +++ b/main.py @@ -403,7 +403,7 @@ def prompt_worker(q, server_instance): hook_breaker_ac10a0.restore_functions() if not asset_seeder.is_disabled(): - asset_seeder.enqueue_enrich(roots=("output",), compute_hashes=True) + asset_seeder.enqueue_enrich(roots=("output",), compute_hashes=args.enable_asset_hashing) asset_seeder.resume() @@ -458,7 +458,7 @@ def setup_database(): if dependencies_available(): init_db() if args.enable_assets: - if asset_seeder.start(roots=("models", "input", "output"), prune_first=True, compute_hashes=True): + if asset_seeder.start(roots=("models", "input", "output"), prune_first=True, compute_hashes=args.enable_asset_hashing): logging.info("Background asset scan initiated for models, input, output") except Exception as e: if "database is locked" in str(e): From b70944e710c1cb7455099d06fd149d0fe47b330e Mon Sep 17 00:00:00 2001 From: Alexander Piskun <13381981+bigcat88@users.noreply.github.com> Date: Wed, 1 Jul 2026 00:17:53 +0300 Subject: [PATCH 2/2] [Partner Nodes] feat(Google): add Gemini Video Omni node (#14695) --- comfy_api_nodes/apis/gemini.py | 1 + comfy_api_nodes/nodes_gemini.py | 174 +++++++++++++++++++++++++++++++- 2 files changed, 174 insertions(+), 1 deletion(-) diff --git a/comfy_api_nodes/apis/gemini.py b/comfy_api_nodes/apis/gemini.py index caaba8f36..7b2543270 100644 --- a/comfy_api_nodes/apis/gemini.py +++ b/comfy_api_nodes/apis/gemini.py @@ -121,6 +121,7 @@ class GeminiGenerationConfig(BaseModel): topK: int | None = Field(None, ge=1) topP: float | None = Field(None, ge=0.0, le=1.0) thinkingConfig: GeminiThinkingConfig | None = Field(None) + responseModalities: list[str] | None = Field(None) class GeminiImageOutputOptions(BaseModel): diff --git a/comfy_api_nodes/nodes_gemini.py b/comfy_api_nodes/nodes_gemini.py index 1a8aadfd6..aa992802d 100644 --- a/comfy_api_nodes/nodes_gemini.py +++ b/comfy_api_nodes/nodes_gemini.py @@ -13,7 +13,7 @@ import torch from typing_extensions import override import folder_paths -from comfy_api.latest import IO, ComfyExtension, Input, Types +from comfy_api.latest import IO, ComfyExtension, Input, InputImpl, Types from comfy_api_nodes.apis.gemini import ( GeminiContent, GeminiFileData, @@ -37,6 +37,7 @@ from comfy_api_nodes.util import ( audio_to_base64_string, bytesio_to_image_tensor, download_url_to_image_tensor, + download_url_to_video_output, get_number_of_images, sync_op, tensor_to_base64_string, @@ -45,6 +46,7 @@ from comfy_api_nodes.util import ( upload_images_to_comfyapi, upload_video_to_comfyapi, validate_string, + validate_video_duration, video_to_base64_string, ) @@ -229,10 +231,29 @@ async def get_image_from_response(response: GeminiGenerateContentResponse, thoug return torch.cat(image_tensors, dim=0) +async def get_video_from_response( + response: GeminiGenerateContentResponse, cls: type[IO.ComfyNode] | None = None +) -> InputImpl.VideoFromFile: + parts = get_parts_by_type(response, "video/*") + for part in parts: + if part.inlineData and part.inlineData.data: + return InputImpl.VideoFromFile(BytesIO(base64.b64decode(part.inlineData.data))) + if part.fileData and part.fileData.fileUri: + return await download_url_to_video_output(part.fileData.fileUri, cls=cls) + model_message = get_text_from_response(response).strip() + if model_message: + raise ValueError(f"Gemini did not generate a video. Model response: {model_message}") + raise ValueError( + "Gemini did not generate a video. Try rephrasing your prompt, " + "shortening the requested duration, or reducing the number of input images/videos." + ) + + def calculate_tokens_price(response: GeminiGenerateContentResponse) -> float | None: if not response.modelVersion: return None # Define prices (Cost per 1,000,000 tokens), see https://cloud.google.com/vertex-ai/generative-ai/pricing + output_video_tokens_price = 0.0 if response.modelVersion == "gemini-2.5-pro": input_tokens_price = 1.25 output_text_tokens_price = 10.0 @@ -265,6 +286,11 @@ def calculate_tokens_price(response: GeminiGenerateContentResponse) -> float | N input_tokens_price = 0.25 output_text_tokens_price = 1.50 output_image_tokens_price = 30.0 + elif response.modelVersion == "gemini-omni-flash-preview": + input_tokens_price = 2.145 + output_text_tokens_price = 12.87 + output_image_tokens_price = 0.0 + output_video_tokens_price = 25.025 else: return None final_price = response.usageMetadata.promptTokenCount * input_tokens_price @@ -272,6 +298,8 @@ def calculate_tokens_price(response: GeminiGenerateContentResponse) -> float | N for i in response.usageMetadata.candidatesTokensDetails: if i.modality == Modality.IMAGE: final_price += output_image_tokens_price * i.tokenCount # for Nano Banana models + elif i.modality == Modality.VIDEO: + final_price += output_video_tokens_price * i.tokenCount # for Omni Flash else: final_price += output_text_tokens_price * i.tokenCount if response.usageMetadata.thoughtsTokenCount: @@ -1531,6 +1559,149 @@ class GeminiNanoBanana2V2(IO.ComfyNode): ) +OMNI_MAX_IMAGES = 14 +OMNI_MAX_VIDEOS = 3 + +OMNI_MODELS: dict[str, str] = { + "Omni Flash": "gemini-omni-flash-preview", +} + + +def _omni_flash_inputs() -> list[Input]: + """Per-model inputs for the Omni video DynamicCombo (prompt + reference media + sampling).""" + return [ + IO.String.Input( + "prompt", + multiline=True, + default="", + tooltip="Describe the video to generate. Specify the length and aspect ratio directly in the " + 'prompt, e.g. "a 6-second clip in 16:9". Length may be 3-10 seconds; the aspect ratio must be ' + "16:9 (landscape) or 9:16 (portrait). The output is 720p, 24 FPS, with audio.", + ), + IO.Autogrow.Input( + "images", + template=IO.Autogrow.TemplateNames( + IO.Image.Input("image"), + names=[f"image_{i}" for i in range(1, OMNI_MAX_IMAGES + 1)], + min=0, + ), + tooltip=f"Optional reference image(s) to guide or animate the video. Up to {OMNI_MAX_IMAGES} images.", + ), + IO.Autogrow.Input( + "videos", + template=IO.Autogrow.TemplateNames( + IO.Video.Input("video"), + names=[f"video_{i}" for i in range(1, OMNI_MAX_VIDEOS + 1)], + min=0, + ), + tooltip=f"Optional reference video(s) to guide or edit. Up to {OMNI_MAX_VIDEOS} videos, " + f"each up to 10 seconds long.", + ), + IO.Float.Input( + "temperature", + default=1.0, + min=0.0, + max=2.0, + step=0.01, + tooltip="Controls randomness. Lower is more focused/deterministic, higher is more varied.", + advanced=True, + ), + IO.Float.Input( + "top_p", + default=0.95, + min=0.0, + max=1.0, + step=0.01, + tooltip="Nucleus sampling: sample from the smallest token set whose cumulative probability reaches top_p.", + advanced=True, + ), + ] + + +class GeminiVideoOmni(IO.ComfyNode): + + @classmethod + def define_schema(cls): + return IO.Schema( + node_id="GeminiVideoOmni", + display_name="Google Gemini Omni (Video)", + category="partner/video/Gemini", + essentials_category="Video Generation", + description="Generate a video with audio from a text prompt using Google's Gemini Omni Flash model. " + "Optionally provide reference images and/or videos to guide or edit the result. Describe the desired " + "length (3-10s) and aspect ratio (16:9 or 9:16) directly in the prompt.", + inputs=[ + IO.DynamicCombo.Input( + "model", + options=[ + IO.DynamicCombo.Option("Omni Flash", _omni_flash_inputs()), + ], + tooltip="The Gemini video model used to generate the video.", + ), + IO.Int.Input( + "seed", + default=42, + min=0, + max=2147483647, + control_after_generate=True, + tooltip="Seed controls whether the node should re-run; " + "results are non-deterministic regardless of seed.", + ), + ], + outputs=[ + IO.Video.Output(), + IO.String.Output(), + ], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=IO.PriceBadge( + expr='{"type":"usd","usd":0.146,"format":{"suffix":"/second","approximate":true}}' + ), + ) + + @classmethod + async def execute(cls, model: dict, seed: int) -> IO.NodeOutput: + prompt = model.get("prompt") or "" + validate_string(prompt, strip_whitespace=True, min_length=1) + model_id = OMNI_MODELS[model["model"]] + + images = [t for t in (model.get("images") or {}).values() if t is not None] + videos = [v for v in (model.get("videos") or {}).values() if v is not None] + if sum(get_number_of_images(t) for t in images) > OMNI_MAX_IMAGES: + raise ValueError(f"The current maximum number of supported images is {OMNI_MAX_IMAGES}.") + if len(videos) > OMNI_MAX_VIDEOS: + raise ValueError(f"The current maximum number of supported videos is {OMNI_MAX_VIDEOS}.") + for video in videos: + validate_video_duration(video, max_duration=10) + + parts: list[GeminiPart] = [] + if images or videos: + parts.extend(await build_gemini_media_parts(cls, images, [], videos)) + parts.append(GeminiPart(text=prompt)) + response = await sync_op( + cls, + ApiEndpoint(path=f"{GEMINI_BASE_ENDPOINT}/{model_id}", method="POST"), + data=GeminiGenerateContentRequest( + contents=[GeminiContent(role=GeminiRole.user, parts=parts)], + generationConfig=GeminiGenerationConfig( + responseModalities=["TEXT", "VIDEO"], + temperature=model.get("temperature", 1.0), + topP=model.get("top_p", 0.95), + ), + ), + response_model=GeminiGenerateContentResponse, + price_extractor=calculate_tokens_price, + ) + return IO.NodeOutput( + await get_video_from_response(response, cls=cls), + get_text_from_response(response), + ) + + class GeminiExtension(ComfyExtension): @override async def get_node_list(self) -> list[type[IO.ComfyNode]]: @@ -1541,6 +1712,7 @@ class GeminiExtension(ComfyExtension): GeminiImage2, GeminiNanoBanana2, GeminiNanoBanana2V2, + GeminiVideoOmni, GeminiInputFiles, ]