From 2a899302a65ddbbfd22ec86f6ef79d7578ca34be Mon Sep 17 00:00:00 2001 From: Aryan Date: Fri, 6 Feb 2026 15:38:38 +0530 Subject: [PATCH] Add .env support for API keys, add input tooltips --- .env.example | 7 ++ README.md | 230 +++++++++++--------------------------- __init__.py | 3 + elevenlabs_tts.py | 4 +- flux2_replicate.py | 6 +- flux_kontext_replicate.py | 4 +- gemini_diarisation.py | 11 +- gemini_node.py | 6 +- gemini_segment.py | 6 +- gemini_tts.py | 4 +- gpt_image_edit.py | 4 +- imagen.py | 4 +- imagen_edit.py | 2 +- nano_banana.py | 4 +- openai_node.py | 4 +- openai_tts.py | 4 +- pyproject.toml | 4 +- requirements.txt | 1 + sora.py | 6 +- veo.py | 2 +- veo_api.py | 4 +- 21 files changed, 115 insertions(+), 205 deletions(-) create mode 100644 .env.example diff --git a/.env.example b/.env.example new file mode 100644 index 0000000..a49a442 --- /dev/null +++ b/.env.example @@ -0,0 +1,7 @@ +# Copy this file to .env and fill in your API keys +# You can reference these variable names directly in the nodes + +GEMINI_API_KEY="your_gemini_api_key" +OPENAI_API_KEY="your_openai_api_key" +XI_API_KEY="your_elevenlabs_api_key" +REPLICATE_API_TOKEN="your_replicate_api_token" \ No newline at end of file diff --git a/README.md b/README.md index ff3c5a1..9651a21 100644 --- a/README.md +++ b/README.md @@ -51,251 +51,149 @@ All nodes in this collection require API keys to function. * **ElevenLabs TTS Node:** You will need an [ElevenLabs API Key](https://elevenlabs.io/). * **Vertex AI Nodes (Imagen Edit, Veo Vertex AI):** You will need a Google Cloud Project ID, a service account with appropriate permissions, and the location for the resources. -You can paste your key directly into the `api_key` field on the corresponding node. For Vertex AI nodes, you will need to provide the project ID, location, and path to your service account JSON file. +You can paste your key directly into the `api_key` field on the corresponding node. For Vertex AI nodes, you will need to provide the project ID, location, and paste your service account JSON content. + +### Using Environment Variables (.env file) + +Instead of pasting API keys directly into nodes, you can store them in a `.env` file: + +1. Copy `.env.example` to `.env` in the node directory +2. Fill in your API keys: + ``` + GEMINI_API_KEY=your_gemini_key_here + OPENAI_API_KEY=your_openai_key_here + XI_API_KEY=your_elevenlabs_key_here + REPLICATE_API_TOKEN=your_replicate_token_here + ``` +3. In the node's `api_key` field, enter the variable name (e.g., `GEMINI_API_KEY`) instead of the actual key + +This keeps your API keys secure and makes it easy to switch between different keys or projects. --- ## 📚 Node Guide +> **Note:** All nodes include standard inputs like `api_key`, `prompt`, `model`, `temperature`, and `seed` where applicable. Only unique or notable inputs are listed below. + ### Flux Kontext Pro / Max -These nodes allow you to transform an input image based on a text prompt. They are ideal for applying artistic styles or making significant conceptual changes to an existing image. +Transform images based on text prompts. Ideal for applying artistic styles or making conceptual changes. * **Category:** `image/edit` -* **Inputs:** - * `image`: The source image to transform. - * `prompt`: A text description of the desired output (e.g., "A vibrant Van Gogh painting", "Make this a 90s cartoon"). - * `replicate_api_token`: Your API token from Replicate. - * `aspect_ratio`: The desired output aspect ratio. `match_input_image` is highly recommended to preserve the original composition. - * `output_format`: `jpg` or `png`. - * `safety_tolerance`: Adjust the content safety filter level. -* **Output:** - * `image`: The generated image. +* **Key Inputs:** `image`, `aspect_ratio` (use `match_input_image` to preserve composition) +* **Output:** `image` ### Flux.2 (Replicate) -Generate images using Black Forest Labs' FLUX.2 models via the Replicate API. +Generate images using FLUX.2 models (Pro, Max, Dev) via Replicate. * **Category:** `image/generation` -* **Inputs:** - * `prompt`: The text prompt for image generation. - * `api_key`: Your Replicate API token. - * `model`: Choose between `flux-2-max`, `flux-2-pro`, or `flux-2-dev`. - * `aspect_ratio`: The desired aspect ratio for the generated image. - * `output_format`: `webp`, `jpg`, or `png`. - * `output_quality`: Quality of the output image (0-100). - * `image_1` to `image_5` (Optional): Input images for image-to-image or control tasks. -* **Output:** - * `image`: The generated image. +* **Key Inputs:** `image_1` to `image_5` (optional, for image-to-image tasks) +* **Output:** `image` ### Gemini Chat -A versatile node for text generation and image/audio analysis. Use it to understand an image's content, analyze audio, or to generate creative text for other nodes. +Multimodal text generation with image and audio analysis capabilities. * **Category:** `text/generation` -* **Inputs:** - * `prompt`: The text prompt or question you want to ask the model. - * `model`: The Gemini model to use (e.g., `gemini-2.5-pro`, `gemini-2.5-flash`). - * `temperature`: Controls the creativity of the output. - * `thinking`: Enables the model's thinking/reasoning process. - * `seed`: Seed for reproducibility. - * `api_key`: Your API key from Google AI Studio. - * `system_instruction` (Optional): Provide context or rules for how the model should behave. - * `thinking_budget` (Optional): Token budget for thinking. - * `image` (Optional): An input image for the model to analyze. - * `audio` (Optional): An input audio for the model to analyze. -* **Output:** - * `response`: The text generated by the Gemini model. +* **Key Inputs:** `thinking`, `thinking_budget`, `system_instruction`, `image` (optional), `audio` (optional) +* **Output:** `response` (text) ### Gemini Segmentation -This node uses a Gemini model to generate segmentation masks for specified objects within an image. +Generate segmentation masks for objects in an image. * **Category:** `image/generation` -* **Inputs:** - * `image`: The source image for segmentation. - * `segment_prompt`: A text description of the objects to segment (e.g., "the car", "all people"). - * `model`: The Gemini model to use. - * `temperature`: Controls randomness. - * `thinking`: Enable thinking process. - * `seed`: Seed for reproducibility. - * `api_key`: Your API key from Google AI Studio. - * `thinking_budget` (Optional): Token budget for thinking. -* **Output:** - * `mask`: A black and white mask of the segmented objects. +* **Key Inputs:** `image`, `segment_prompt` (e.g., "the car", "all people"), `thinking`, `thinking_budget` +* **Output:** `mask` ### Gemini Speaker Diarization -Separate audio into different speaker tracks using Gemini. +Separate audio into different speaker tracks. * **Category:** `audio/diarise` -* **Inputs:** - * `audio`: The input audio to process. - * `num_speakers`: The expected number of speakers. - * `model`: The Gemini model to use. - * `api_key`: Your API key from Google AI Studio. - * `seed`: Seed for reproducibility. - * `temperature`: Controls randomness. - * `thinking` (Optional): Enable thinking process. - * `thinking_budget` (Optional): Token budget for thinking. -* **Output:** - * `speaker_1` to `speaker_4`: Audio tracks for up to 4 separated speakers. +* **Key Inputs:** `audio`, `num_speakers`, `thinking`, `thinking_budget` +* **Output:** `speaker_1` to `speaker_4` (audio tracks) ### GPT Image Edit -This node uses OpenAI's API to perform powerful, prompt-based inpainting and editing. +Prompt-based inpainting and image editing using OpenAI's API. * **Category:** `image/edit` -* **Inputs:** - * `image`: The source image to edit. - * `mask` (Optional): A black and white mask. The model will edit the **white area** of the mask. - * `prompt`: A description of the edit to perform. - * `api_key`: Your API key from OpenAI. - * `...other_params`: Various quality and formatting options for the OpenAI API. -* **Output:** - * `image`: The edited image. +* **Key Inputs:** `image_1` to `image_5`, `mask` (optional, white area = edit region), `background`, `quality`, `size` +* **Output:** `image` ### OpenAI LLM -Access OpenAI's powerful language models for text generation and reasoning. +Access OpenAI language models (GPT-4, GPT-5, o1, etc.) for text generation. * **Category:** `text/generation` -* **Inputs:** - * `prompt`: The text prompt. - * `model`: The OpenAI model to use (e.g., `gpt-4.1`, `o1`, `gpt-5`). - * `temperature`: Controls randomness. - * `reasoning_effort`: Effort level for reasoning models. - * `api_key`: Your OpenAI API key. - * `max_output_tokens`: Maximum number of tokens to generate. - * `system_instruction` (Optional): System level instructions. - * `image` (Optional): Input image for multimodal models. -* **Output:** - * `response`: The generated text response. +* **Key Inputs:** `reasoning_effort` (low/medium/high), `max_output_tokens`, `system_instruction`, `image` (optional) +* **Output:** `response` (text) ### OpenAI Text-to-Speech -Generate high-quality speech from text using OpenAI's TTS models. +Generate speech using OpenAI's TTS models. * **Category:** `audio/generation` -* **Inputs:** - * `text`: The text to convert to speech. - * `model`: The TTS model to use (e.g., `gpt-4o-mini-tts`, `tts-1`). - * `voice`: The voice to use (e.g., `alloy`, `echo`). - * `response_format`: Output audio format. - * `speed`: Speaking speed. - * `api_key`: Your OpenAI API key. - * `instructions` (Optional): Instructions for the model (supported by some models). -* **Output:** - * `audio`: The generated audio. +* **Key Inputs:** `text`, `voice` (alloy, echo, etc.), `response_format`, `speed`, `instructions` (optional) +* **Output:** `audio` ### Google Imagen Generator -Generate images from a text prompt using Google's Imagen models. +Generate images from text using Google's Imagen models. * **Category:** `image/generation` -* **Inputs:** - * `prompt`: A text description of the image to generate. - * `api_key`: Your API key from Google AI Studio. - * `model`: The Imagen model to use. - * `...other_params`: Options for number of images, aspect ratio, and image size. -* **Output:** - * `images`: The generated image(s). +* **Key Inputs:** `number_of_images`, `aspect_ratio`, `image_size`, `guidance_scale`, `negative_prompt` +* **Output:** `images` ### Google Imagen Edit (Vertex AI only) -Perform advanced image editing, inpainting, outpainting, and background swapping using Imagen on Google's Vertex AI platform. +Advanced image editing with inpainting, outpainting, and background swapping. * **Category:** `image/edit` -* **Inputs:** - * `image`: The source image to edit. - * `mask`: A mask defining the area to edit. - * `prompt`: A description of the desired edit. - * `project_id`: Your Google Cloud Project ID. - * `location`: The Google Cloud location for the model. - * `service_account`: Path to your Google Cloud service account JSON file. - * `edit_mode`: The type of edit to perform (e.g., inpainting, outpainting). - * `...other_params`: Controls for negative prompt, seed, and steps. -* **Output:** - * `edited_images`: The edited image(s). +* **Key Inputs:** `image`, `mask`, `project_id`, `location`, `service_account` (JSON content), `edit_mode` +* **Output:** `edited_images` ### Nano Banana -A creative image generation node that can take a combination of text and up to five images as input. +Creative image generation using a specialized Gemini model. * **Category:** `image/generation` -* **Inputs:** - * `api_key`: Your API key from Google AI Studio. - * `prompt` (Optional): A text prompt. - * `image_1` to `image_5` (Optional): Up to five source images. - * `...other_params`: Controls for aspect ratio, temperature, top_p, and seed. -* **Output:** - * `image`: The generated image. +* **Key Inputs:** `image_1` to `image_5` (optional), `aspect_ratio`, `resolution`, `top_p` +* **Output:** `image` ### Veo Video Generator (Vertex AI) -Generate short, high-quality video clips from a text description using Google's Veo model on Vertex AI. +Generate video clips using Google's Veo model on Vertex AI. * **Category:** `video/generation` -* **Inputs:** - * `prompt`: A text description of the video to generate. - * `project_id`: Your Google Cloud Project ID. - * `location`: The Google Cloud location for the model. - * `service_account`: Path to your Google Cloud service account JSON file. - * `...other_params`: Controls for negative prompt, aspect ratio, audio generation, and seed. -* **Output:** - * `frames`: The generated video frames, output as an image batch. +* **Key Inputs:** `project_id`, `location`, `service_account` (JSON content), `resolution`, `aspect_ratio`, `duration_seconds`, `generate_audio`, `first_frame`/`last_frame` (optional) +* **Output:** `frames`, `audio` ### Veo Video Generator (Gemini API) -Generate videos using Google's Veo 2.0 model via the Gemini API. Supports text-to-video and image-to-video. +Generate videos using Veo 2.0 via the Gemini API. Supports text-to-video and image-to-video. * **Category:** `video/generation` -* **Inputs:** - * `prompt`: A text description of the video. - * `image` (Optional): An input image for image-to-video generation. - * `api_key`: Your API key from Google AI Studio. - * `model`: The Veo model to use (e.g., `veo-2.0-generate-001`). - * `aspect_ratio`: Desired aspect ratio (16:9 or 9:16). - * `duration_seconds`: Duration of the video (e.g., 5-8 seconds). - * `...other_params`: Controls for negative prompt and seed. -* **Output:** - * `frames`: The generated video frames. +* **Key Inputs:** `aspect_ratio`, `duration_seconds`, `negative_prompt`, `image` (optional, for image-to-video) +* **Output:** `frames` ### ElevenLabs TTS -Generate speech from text using the ElevenLabs API. +Generate speech using ElevenLabs' diverse voices and models. * **Category:** `audio/generation` -* **Inputs:** - * `text`: The text to convert to speech. - * `api_key`: Your API key from ElevenLabs. - * `voice_id`: The ID of the voice to use for generation. - * `model_id`: The ElevenLabs model to use. - * `output_format`: The desired output audio format. - * `stability`: Controls the stability and variability of the generated speech. - * `similarity_boost`: Enhances the similarity of the generated speech to the chosen voice. - * `speed`: Adjusts the speaking rate. - * `style`: Controls the expressiveness of the speech. - * `use_speaker_boost`: A boolean to enable or disable speaker boost. - * `seed`: A seed for ensuring reproducible results. -* **Output:** - * `audio`: The generated audio waveform and sample rate. +* **Key Inputs:** `text`, `voice_id`, `model_id`, `stability`, `similarity_boost`, `speed`, `style`, `use_speaker_boost` +* **Output:** `audio` ### Gemini TTS -Generate speech from text using Google's Gemini TTS models. +Generate speech using Google's Gemini TTS models. * **Category:** `audio/generation` -* **Inputs:** - * `text`: The text to be converted into speech. - * `api_key`: Your API key from Google AI Studio. - * `model`: The specific Gemini model to use for generation. - * `voice_id`: The prebuilt voice to use for the output. - * `temperature`: Controls the randomness and creativity of the output. - * `seed`: A seed for ensuring reproducible results. - * `system_prompt` (Optional): A system-level instruction to guide the model's behavior. -* **Output:** - * `audio`: The generated audio waveform and sample rate. +* **Key Inputs:** `text`, `voice_id`, `system_prompt` (optional) +* **Output:** `audio` ## Acknowledgements diff --git a/__init__.py b/__init__.py index 54f74f7..7e4a4c2 100644 --- a/__init__.py +++ b/__init__.py @@ -1,3 +1,6 @@ +from dotenv import load_dotenv +load_dotenv() + from .flux_kontext_replicate import NODE_CLASS_MAPPINGS as PRO_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS as PRO_DISPLAY from .gemini_node import NODE_CLASS_MAPPINGS as GEMINI_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS as GEMINI_DISPLAY from .gemini_diarisation import NODE_CLASS_MAPPINGS as GEMINI_DIAR_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS as GEMINI_DIAR_DISPLAY diff --git a/elevenlabs_tts.py b/elevenlabs_tts.py index 64ba3d5..5f97266 100644 --- a/elevenlabs_tts.py +++ b/elevenlabs_tts.py @@ -48,7 +48,7 @@ class ElevenLabsTTSNode: "style": ("FLOAT", {"default": 0.50, "min": 0.0, "max": 1.0, "step": 0.01}), "use_speaker_boost": ("BOOLEAN", {"default": True}), "seed": ("INT", {"default": 40, "min": 0, "max": 4294967294}), - "api_key": ("STRING", {"multiline": False, "default": ""}), + "api_key": ("STRING", {"multiline": False, "default": "", "tooltip": "Directly put ElevenLabs API key or .env variable name (XI_API_KEY)"}), }, "optional": { "previous_text": ("STRING", {"multiline": True, "default": ""}), @@ -68,7 +68,7 @@ class ElevenLabsTTSNode: if not text.strip(): raise ValueError("Text input cannot be empty.") - key = api_key.strip() or os.environ.get("XI_API_KEY") + key = os.environ.get(api_key.strip(), api_key.strip()) or os.environ.get("XI_API_KEY") if not key: raise ValueError("No API key provided.") diff --git a/flux2_replicate.py b/flux2_replicate.py index e246b31..2c0825e 100644 --- a/flux2_replicate.py +++ b/flux2_replicate.py @@ -12,7 +12,7 @@ class Flux2Replicate: return { "required": { "prompt": ("STRING", {"multiline": True, "default": "A beautiful landscape"}), - "api_key": ("STRING", {"default": ""}), + "api_key": ("STRING", {"default": "", "tooltip": "Directly put Replicate API token or .env variable name (REPLICATE_API_TOKEN)"}), "model": (["flux-2-max", "flux-2-pro", "flux-2-dev"], {"default": "flux-2-max"}), "aspect_ratio": (["1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3", "5:4", "4:5", "21:9", "9:21", "2:1", "1:2"], {"default": "1:1"}), "output_format": (["webp", "jpg", "png"], {"default": "webp"}), @@ -49,7 +49,7 @@ class Flux2Replicate: def generate_image(self, prompt, api_key, model, aspect_ratio, output_format, output_quality, image_1=None, image_2=None, image_3=None, image_4=None, image_5=None): try: - os.environ["REPLICATE_API_TOKEN"] = api_key + os.environ["REPLICATE_API_TOKEN"] = os.environ.get(api_key.strip(), api_key.strip()) or os.environ.get("REPLICATE_API_TOKEN", "") input_images = [] for img in [image_1, image_2, image_3, image_4, image_5]: @@ -68,7 +68,7 @@ class Flux2Replicate: # Add safety_tolerance for models that support it (flux-2-max and flux-2-pro) if model in ["flux-2-max", "flux-2-pro"]: - replicate_input["safety_tolerance"] = 0 + replicate_input["safety_tolerance"] = 1 # Run Replicate model output = replicate.run( diff --git a/flux_kontext_replicate.py b/flux_kontext_replicate.py index c0c9029..9a6b251 100644 --- a/flux_kontext_replicate.py +++ b/flux_kontext_replicate.py @@ -13,7 +13,7 @@ class FluxKontextReplicate: "required": { "image": ("IMAGE",), "prompt": ("STRING", {"multiline": True, "default": "Make this a 90s cartoon"}), - "api_key": ("STRING", {"default": ""}), + "api_key": ("STRING", {"default": "", "tooltip": "Directly put Replicate API token or .env variable name (REPLICATE_API_TOKEN)"}), "model": (["flux-kontext-dev", "flux-kontext-max", "flux-kontext-pro"], {"default": "flux-kontext-dev"}), "aspect_ratio": (["1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3", "5:4", "4:5", "21:9", "9:21", "2:1", "1:2", "match_input_image"], {"default": "match_input_image"}), "output_format": (["jpg", "png"], {"default": "jpg"}), @@ -30,7 +30,7 @@ class FluxKontextReplicate: def generate_image(self, image, prompt, api_key, model, aspect_ratio, output_format, safety_tolerance, seed, prompt_upsampling): try: - os.environ["REPLICATE_API_TOKEN"] = api_key + os.environ["REPLICATE_API_TOKEN"] = os.environ.get(api_key.strip(), api_key.strip()) or os.environ.get("REPLICATE_API_TOKEN", "") # Convert tensor to PIL and save to buffer tensor = image.squeeze(0) if len(image.shape) == 4 else image diff --git a/gemini_diarisation.py b/gemini_diarisation.py index cb2bac3..5e838ca 100644 --- a/gemini_diarisation.py +++ b/gemini_diarisation.py @@ -16,18 +16,18 @@ class GeminiDiarisationAPI: "audio": ("AUDIO",), "num_speakers": ("INT", {"default": 2, "min": 1, "max": 10, "step": 1}), "model": ("STRING", {"default": "gemini-2.5-flash", "multiline": False}), - "api_key": ("STRING", {"default": "", "multiline": False}), + "api_key": ("STRING", {"default": "", "multiline": False, "tooltip": "Directly put Gemini API key or .env variable name (GEMINI_API_KEY)"}), "seed": ("INT", {"default": 69, "min": 0, "max": 2147483646, "step": 1}), "temperature": ("FLOAT", {"default": 0.2, "min": 0.0, "max": 2.0, "step": 0.1}) }, "optional": { "thinking": ("BOOLEAN", {"default": False}), - "thinking_budget": ("INT", {"default": 1024, "min": 0, "max": 24576, "step": 1}), + "thinking_budget": ("INT", {"default": 1024, "min": 0, "max": 24576, "step": 1, "tooltip": "-1 = auto, 0 = disabled, 1+ = token budget"}), } } - RETURN_TYPES = ("AUDIO", "AUDIO", "AUDIO", "AUDIO", "STRING") - RETURN_NAMES = ("speaker_1", "speaker_2", "speaker_3", "speaker_4", "json") + RETURN_TYPES = ("AUDIO", "AUDIO", "AUDIO", "AUDIO") + RETURN_NAMES = ("speaker_1", "speaker_2", "speaker_3", "speaker_4") FUNCTION = "diarise" CATEGORY = "audio/diarise" @@ -64,7 +64,7 @@ class GeminiDiarisationAPI: w.writeframes((audio_np * 32767).astype(np.int16).tobytes()) # 2. Setup Client - key = api_key.strip() or os.environ.get("GEMINI_API_KEY") + key = os.environ.get(api_key.strip(), api_key.strip()) or os.environ.get("GEMINI_API_KEY") if not key: raise ValueError("API Key missing") client = genai.Client(api_key=key, http_options={'api_version': 'v1beta'}) @@ -149,7 +149,6 @@ class GeminiDiarisationAPI: tensor = torch.from_numpy(track).float().unsqueeze(0).unsqueeze(0) outputs.append({"waveform": tensor, "sample_rate": sr}) - outputs.append(json.dumps(result, indent=2)) return tuple(outputs) NODE_CLASS_MAPPINGS = {"GeminiDiarisationAPI": GeminiDiarisationAPI} diff --git a/gemini_node.py b/gemini_node.py index 0e7fc86..62633ba 100644 --- a/gemini_node.py +++ b/gemini_node.py @@ -17,11 +17,11 @@ class GeminiChatNode: "temperature": ("FLOAT", {"default": 0.2, "min": 0.0, "max": 2.0, "step": 0.1}), "thinking": ("BOOLEAN", {"default": False}), "seed": ("INT", {"default": 69, "min": -1, "max": 2147483646, "step": 1}), - "api_key": ("STRING", {"default": "", "multiline": False}) + "api_key": ("STRING", {"default": "", "multiline": False, "tooltip": "Directly put Gemini API key or .env variable name (GEMINI_API_KEY)"}) }, "optional": { "system_instruction": ("STRING", {"multiline": True, "default": ""}), - "thinking_budget": ("INT", {"default": 0, "min": -1, "max": 24576, "step": 1}), + "thinking_budget": ("INT", {"default": 0, "min": -1, "max": 24576, "step": 1, "tooltip": "-1 = auto, 0 = disabled"}), "image": ("IMAGE",), "audio": ("AUDIO",), } @@ -35,7 +35,7 @@ class GeminiChatNode: def generate(self, prompt, model, temperature, thinking, seed, api_key, system_instruction=None, thinking_budget=-1, image=None, audio=None): - key = api_key.strip() or os.environ.get("GEMINI_API_KEY") + key = os.environ.get(api_key.strip(), api_key.strip()) or os.environ.get("GEMINI_API_KEY") if not key: raise ValueError("Error: No API key provided.") client = genai.Client(api_key=key, http_options={'api_version': 'v1beta'}) diff --git a/gemini_segment.py b/gemini_segment.py index f9b0dab..cabef81 100644 --- a/gemini_segment.py +++ b/gemini_segment.py @@ -20,10 +20,10 @@ class GeminiSegmentationNode: "temperature": ("FLOAT", {"default": 0.0, "min": 0.0, "max": 2.0, "step": 0.1}), "thinking": ("BOOLEAN", {"default": False}), "seed": ("INT", {"default": 69, "min": -1, "max": 2147483646, "step": 1}), - "api_key": ("STRING", {"default": "", "multiline": False}) + "api_key": ("STRING", {"default": "", "multiline": False, "tooltip": "Directly put Gemini API key or .env variable name (GEMINI_API_KEY)"}) }, "optional": { - "thinking_budget": ("INT", {"default": 0, "min": -1, "max": 24576, "step": 1}), + "thinking_budget": ("INT", {"default": 0, "min": -1, "max": 24576, "step": 1, "tooltip": "-1 = auto, 0 = disabled"}), } } @@ -33,7 +33,7 @@ class GeminiSegmentationNode: CATEGORY = "image/generation" def generate_segmentation(self, image, segment_prompt, model, temperature, thinking, seed, api_key, thinking_budget=0): - key = api_key.strip() or os.environ.get("GEMINI_API_KEY") or os.environ.get("GOOGLE_API_KEY") + key = os.environ.get(api_key.strip(), api_key.strip()) or os.environ.get("GEMINI_API_KEY") or os.environ.get("GOOGLE_API_KEY") if not key: raise ValueError("API Key missing") client = genai.Client(api_key=key, http_options={'api_version': 'v1beta'}) diff --git a/gemini_tts.py b/gemini_tts.py index 9582b1b..0245a85 100644 --- a/gemini_tts.py +++ b/gemini_tts.py @@ -9,7 +9,7 @@ class GeminiTTSNode: return { "required": { "text": ("STRING", {"multiline": True, "default": ""}), - "api_key": ("STRING", {"multiline": False, "default": ""}), + "api_key": ("STRING", {"multiline": False, "default": "", "tooltip": "Directly put Gemini API key or .env variable name (GEMINI_API_KEY)"}), "model": (["gemini-2.5-flash-preview-tts", "gemini-2.5-pro-preview-tts"],), "voice_id": (["Zephyr", "Puck", "Charon", "Kore", "Fenrir", "Leda", "Orus", "Aoede", "Callirrhoe", "Autonoe", "Enceladus", "Iapetus", "Umbriel", "Algieba", "Despina", "Erinome", "Achernar", "Laomedeia", "Rasalgethi", "Algenib", "Achird", "Pulcherrima", "Gacrux", "Schedar", "Alnilam", "Sulafat", "Sadaltager", "Sadachbia", "Vindemiatrix", "Zubenelgenubi"],), "seed": ("INT", {"default": 69, "min": -1, "max": 2147483646, "step": 1}), @@ -30,7 +30,7 @@ class GeminiTTSNode: if not text.strip(): raise ValueError("Text input cannot be empty.") - key = api_key.strip() or os.environ.get("GEMINI_API_KEY") + key = os.environ.get(api_key.strip(), api_key.strip()) or os.environ.get("GEMINI_API_KEY") if not key: raise ValueError("No API key provided.") diff --git a/gpt_image_edit.py b/gpt_image_edit.py index 84a483c..e61fd49 100644 --- a/gpt_image_edit.py +++ b/gpt_image_edit.py @@ -15,7 +15,7 @@ class GPTImageEditNode: "image_1": ("IMAGE",), "model": (["gpt-image-1", "gpt-image-1-mini", "gpt-image-1.5"],), "prompt": ("STRING", {"multiline": True, "default": "Edit this image"}), - "api_key": ("STRING", {"multiline": False, "default": ""}), + "api_key": ("STRING", {"multiline": False, "default": "", "tooltip": "Directly put OpenAI API key or .env variable name (OPENAI_API_KEY)"}), "background": (["auto", "transparent", "opaque"], {"default": "auto"}), "quality": (["auto", "high", "medium", "low"], {"default": "auto"}), "size": (["auto", "1024x1024", "1536x1024", "1024x1536"], {"default": "auto"}), @@ -56,7 +56,7 @@ class GPTImageEditNode: def edit_image(self, image_1, model, prompt, api_key, background, quality, size, output_format, output_compression, n_images, mask=None, **kwargs): - key = api_key.strip() or os.environ.get("OPENAI_API_KEY") + key = os.environ.get(api_key.strip(), api_key.strip()) or os.environ.get("OPENAI_API_KEY") if not key: raise ValueError("GPT Image Edit: No API Key provided.") diff --git a/imagen.py b/imagen.py index 315a9db..a6ced2b 100644 --- a/imagen.py +++ b/imagen.py @@ -12,7 +12,7 @@ class GoogleImagenNode: return { "required": { "prompt": ("STRING", {"multiline": True}), - "api_key": ("STRING", {"multiline": False, "default": ""}), + "api_key": ("STRING", {"multiline": False, "default": "", "tooltip": "Directly put Gemini API key or .env variable name (GEMINI_API_KEY)"}), "model": (["models/imagen-4.0-ultra-generate-001", "models/imagen-4.0-generate-001", "models/imagen-4.0-fast-generate-001", "models/imagen-3.0-generate-002"],), "number_of_images": ("INT", {"default": 1, "min": 1, "max": 4, "step": 1}), "aspect_ratio": (["1:1", "9:16", "16:9", "4:3", "3:4"],), @@ -31,7 +31,7 @@ class GoogleImagenNode: CATEGORY = "image/generation" def generate_images(self, prompt, api_key, model, number_of_images, aspect_ratio, image_size, seed, guidance_scale, negative_prompt=""): - key = api_key.strip() or os.environ.get("GEMINI_API_KEY") + key = os.environ.get(api_key.strip(), api_key.strip()) or os.environ.get("GEMINI_API_KEY") if not key: raise ValueError("No API key provided.") client = genai.Client(api_key=key) diff --git a/imagen_edit.py b/imagen_edit.py index 2d9c8ce..9848aa5 100644 --- a/imagen_edit.py +++ b/imagen_edit.py @@ -19,7 +19,7 @@ class GoogleImagenEditNode: "prompt": ("STRING", {"multiline": True, "default": "Edit this image"}), "project_id": ("STRING", {"multiline": False, "default": ""}), "location": (["global", "us-central1", "us-east1", "us-east4", "us-east5", "us-south1", "us-west1", "us-west2", "us-west3", "us-west4", "northamerica-northeast1", "northamerica-northeast2", "southamerica-east1", "southamerica-west1", "africa-south1", "europe-west1", "europe-north1", "europe-west2", "europe-west3", "europe-west4", "europe-west6", "europe-west8", "europe-west9", "europe-west12", "europe-southwest1", "europe-central2", "asia-east1", "asia-east2", "asia-northeast1", "asia-northeast2", "asia-northeast3", "asia-south1", "asia-south2", "asia-southeast1", "asia-southeast2", "australia-southeast1", "australia-southeast2", "me-central1", "me-central2", "me-west1"], {"default": "us-central1"}), - "service_account": ("STRING", {"multiline": True, "default": ""}), + "service_account": ("STRING", {"multiline": True, "default": "", "tooltip": "Paste service account JSON content"}), "edit_mode": (["EDIT_MODE_INPAINT_INSERTION", "EDIT_MODE_INPAINT_REMOVAL", "EDIT_MODE_OUTPAINT", "EDIT_MODE_BGSWAP"], {"default": "EDIT_MODE_INPAINT_INSERTION"}), "number_of_images": ("INT", {"default": 1, "min": 1, "max": 4, "step": 1}), "seed": ("INT", {"default": 69, "min": 1, "max": 2147483646, "step": 1}), diff --git a/nano_banana.py b/nano_banana.py index 4a315eb..45d5c54 100644 --- a/nano_banana.py +++ b/nano_banana.py @@ -13,7 +13,7 @@ class NanoBananaNode: return { "required": { "prompt": ("STRING", {"multiline": True, "default": ""}), - "api_key": ("STRING", {"multiline": False, "default": ""}), + "api_key": ("STRING", {"multiline": False, "default": "", "tooltip": "Directly put Gemini API key or .env variable name (GEMINI_API_KEY)"}), "model": (["gemini-3-pro-image-preview", "gemini-2.5-flash-image"],), "aspect_ratio": (["1:1", "2:3", "3:2", "3:4", "4:3", "9:16", "16:9", "21:9"],), "resolution": (["1K", "2K", "4K"], {"default": "1K"}), @@ -48,7 +48,7 @@ class NanoBananaNode: def generate(self, api_key, model, aspect_ratio, resolution, temperature, top_p, seed, prompt="", system_instruction="", **kwargs): - key = api_key.strip() or os.environ.get("GEMINI_API_KEY") + key = os.environ.get(api_key.strip(), api_key.strip()) or os.environ.get("GEMINI_API_KEY") if not key: raise ValueError("No API key provided.") diff --git a/openai_node.py b/openai_node.py index 04a1d7b..b15ec75 100644 --- a/openai_node.py +++ b/openai_node.py @@ -16,7 +16,7 @@ class OpenAILLMNode: "model": (["gpt-4.1","gpt-4.1-mini","gpt-5","gpt-5.2","gpt-5-mini","gpt-5-nano","gpt-5.2-pro","o1","o3-mini"],), "temperature": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 2.0, "step": 0.01}), "reasoning_effort": (["low", "medium", "high"],), - "api_key": ("STRING", {"multiline": False, "default": ""}), + "api_key": ("STRING", {"multiline": False, "default": "", "tooltip": "Directly put OpenAI API key or .env variable name (OPENAI_API_KEY)"}), "max_output_tokens": ("INT", {"default": 16384, "min": 1, "max": 32768, "step": 1}) }, "optional": { @@ -36,7 +36,7 @@ class OpenAILLMNode: if not prompt.strip(): raise ValueError("Prompt cannot be empty.") - key = api_key.strip() or os.environ.get("OPENAI_API_KEY") + key = os.environ.get(api_key.strip(), api_key.strip()) or os.environ.get("OPENAI_API_KEY") if not key: raise ValueError("No API key provided.") diff --git a/openai_tts.py b/openai_tts.py index f8d3b0d..96c4864 100644 --- a/openai_tts.py +++ b/openai_tts.py @@ -36,7 +36,7 @@ class OpenAITTSNode: "pcm" ],), "speed": ("FLOAT", {"default": 1.0, "min": 0.25, "max": 4.0, "step": 0.01}), - "api_key": ("STRING", {"multiline": False, "default": ""}), + "api_key": ("STRING", {"multiline": False, "default": "", "tooltip": "Directly put OpenAI API key or .env variable name (OPENAI_API_KEY)"}), }, "optional": { "instructions": ("STRING", {"multiline": True, "default": ""}), @@ -53,7 +53,7 @@ class OpenAITTSNode: if not text.strip(): raise ValueError("Text input cannot be empty.") - key = api_key.strip() or os.environ.get("OPENAI_API_KEY") + key = os.environ.get(api_key.strip(), api_key.strip()) or os.environ.get("OPENAI_API_KEY") if not key: raise ValueError("No API key provided. Set OPENAI_API_KEY environment variable or provide it in the node.") diff --git a/pyproject.toml b/pyproject.toml index 79c7ffd..a05a4d3 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,7 +1,7 @@ [project] name = "externalapi-helpers" description = "Various ComfyUI nodes for Gemini, Replicate and OpenAI" -version = "1.0.6" +version = "1.0.7" license = {file = "LICENSE"} # classifiers = [ # # For OS-independent nodes (works on all operating systems) @@ -20,7 +20,7 @@ license = {file = "LICENSE"} # "Environment :: GPU :: Apple Metal", # Apple Metal support # ] -dependencies = ["replicate", "pillow", "numpy", "torch", "google-genai", "opencv-python", "soundfile", "openai", "av"] +dependencies = ["replicate", "pillow", "numpy", "torch", "google-genai", "opencv-python", "soundfile", "openai", "av", "python-dotenv"] [project.urls] Repository = "https://github.com/Aryan185/ComfyUI-ExternalAPI-Helpers" diff --git a/requirements.txt b/requirements.txt index 41e0247..82f8935 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,3 +1,4 @@ +python-dotenv replicate pillow numpy diff --git a/sora.py b/sora.py index 33e663a..49ef924 100644 --- a/sora.py +++ b/sora.py @@ -12,7 +12,7 @@ class SoraGen: return { "required": { "prompt": ("STRING", {"multiline": True, "default": "A calico cat playing a piano on stage"}), - "api_key": ("STRING", {"multiline": False, "default": ""}), + "api_key": ("STRING", {"multiline": False, "default": "", "tooltip": "Directly put OpenAI API key or .env variable name (OPENAI_API_KEY)"}), "model": (["sora-2", "sora-2-pro"], {"default": "sora-2"}), "size": (["720x1280", "1280x720", "1024x1792", "1792x1024"], {"default": "1280x720"}), "duration": (["4", "8", "12"], {"default": "4"}), @@ -28,7 +28,9 @@ class SoraGen: OUTPUT_IS_LIST = (True, False) def generate_video(self, prompt, api_key, model, size, duration, seed, input_image=None): - client = OpenAI(api_key=api_key) + key = os.environ.get(api_key.strip(), api_key.strip()) or os.environ.get("OPENAI_API_KEY") + if not key: raise ValueError("No API key provided.") + client = OpenAI(api_key=key) api_args = {"prompt": prompt, "model": model, "size": size, "seconds": duration} img_buf = None diff --git a/veo.py b/veo.py index c6b7a73..fdfb123 100644 --- a/veo.py +++ b/veo.py @@ -29,7 +29,7 @@ class VeoVertexVideoGenerator: "asia-southeast2", "australia-southeast1", "australia-southeast2", "me-central1", "me-central2", "me-west1" ], {"default": "us-central1"}), - "service_account": ("STRING", {"multiline": True, "default": ""}), + "service_account": ("STRING", {"multiline": True, "default": "", "tooltip": "Paste service account JSON content"}), "model": ([ "veo-2.0-generate-001", "veo-2.0-generate-exp", "veo-2.0-generate-preview", "veo-3.0-generate-001", "veo-3.0-fast-generate-001", diff --git a/veo_api.py b/veo_api.py index 450f178..fb469c7 100644 --- a/veo_api.py +++ b/veo_api.py @@ -17,7 +17,7 @@ class VeoGeminiVideoGenerator: "model": (["veo-2.0-generate-001"], {"default": "veo-2.0-generate-001"}), "aspect_ratio": (["16:9", "9:16"], {"default": "16:9"}), "duration_seconds": ("INT", {"default": 8, "min": 5, "max": 8, "step": 1}), - "api_key": ("STRING", {"default": "", "multiline": False}), + "api_key": ("STRING", {"default": "", "multiline": False, "tooltip": "Directly put Gemini API key or .env variable name (GEMINI_API_KEY)"}), "seed": ("INT", {"default": 69, "min": -1, "max": 2147483646, "step": 1}), }, "optional": { @@ -36,7 +36,7 @@ class VeoGeminiVideoGenerator: negative_prompt=None, image=None): # 1. Setup Client - key = api_key.strip() or os.environ.get("GEMINI_API_KEY") + key = os.environ.get(api_key.strip(), api_key.strip()) or os.environ.get("GEMINI_API_KEY") if not key: raise ValueError("API Key required") client = genai.Client(http_options={"api_version": "v1beta"}, api_key=key)