comfyui-stillfront

SFLLMChat

No hay una descripción breve disponible para este nodo.

Stillfront/LLM · 2 salidas

SFPromptList

"

Stillfront/Utils · 1 salida

SFQwenResolution

A node for selecting Qwen model resolutions with visual preview. Class methods ------------- INPUT_TYPES (dict): Defines the resolution selection input. Attributes ---------- RETURN_TYPES (`tuple`): Returns width (INT), height (INT), resolution string (STRING), and preview image (IMAGE). RETURN_NAMES (`tuple`): Names for the outputs: width, height, resolution, preview. FUNCTION (`str`): Entry-point method name: "get_dimensions". OUTPUT_NODE (`bool`): True - this node outputs a preview image. CATEGORY (`str`): UI category: "ControlAltAI Nodes/Qwen". get_dimensions(resolution) -> tuple: Returns the width, height, resolution string, and preview image for the selected resolution.

Stillfront/Utils · 0 entradas · 1 parámetro · 4 salidas

SFTextAnalyzer

"

Stillfront/Utils · 0 entradas · 1 parámetro · 3 salidas

SFVertexAIImagen3TextToImage

Generates images from text prompts using Google Vertex AI Imagen 3.0 models. Supports multiple Imagen 3.0 model variants including standard, fast, and capability models with configurable aspect ratios, safety settings, and output options.

Stillfront/VertexAI · 0 entradas · 12 parámetros · 1 salida

SFVertexAIImagen4TextToImage

Generates images from text prompts using Google Vertex AI Imagen 4.0 models. Supports multiple Imagen 4.0 model variants including standard, fast, and ultra models with configurable aspect ratios, image sizes, safety settings, and output options. Imagen 4.0 supports higher resolutions (up to 2K) for standard and ultra models.

Stillfront/VertexAI · 0 entradas · 12 parámetros · 1 salida

SFVertexAIImagen4Upscale

Upscales images using Google Vertex AI Imagen 4.0 upscale model. This node increases the resolution of images without losing detail. Supports upscale factors from 2x to 4x with a maximum output of 17 megapixels. The output aspect ratio matches the input image.

Stillfront/VertexAI · 1 entrada · 6 parámetros · 1 salida

SFVertexAINanaBananaPro

Generates images from text prompts using Google Vertex AI Nano Banana models. - Nano Banana Pro (gemini-3-pro-image-preview): Up to 4096px (4K), best quality, preview - Nano Banana (gemini-2.5-flash-image): Up to 1024px (1K), faster, stable Pure text-to-image generation. For image editing, use the Edit node.

Stillfront/VertexAI · 3 salidas

SFVertexAINanaBananaProEdit

Edits images using text instructions with Google Vertex AI Nano Banana models. - Nano Banana Pro (gemini-3-pro-image-preview): Up to 4096px (4K), best quality, preview - Nano Banana (gemini-2.5-flash-image): Up to 1024px (1K), faster, stable Supports up to 14 input images for editing, style transfer, and combining elements. Set inputcount and click "Update inputs" button to add more image slots.

Stillfront/VertexAI · 3 salidas

SFVertexAIVeo31ImageToVideo

Generates videos from images using Google Vertex AI Veo 3.1 models. Supports image-to-video generation with an optional last frame for transitions. Configurable duration, resolution, aspect ratio, and audio generation.

Stillfront/VertexAI · 2 entradas · 12 parámetros · 1 salida

SFVertexAIVeo31TextToVideo

Generates videos from text prompts using Google Vertex AI Veo 3.1 models. Supports text-to-video generation with configurable duration, resolution, aspect ratio, and audio generation. Returns video as ComfyUI VIDEO type or saves to GCS.

Stillfront/VertexAI · 0 entradas · 12 parámetros · 1 salida

SFWaveSpeedClient

WaveSpeed AI API Client Node This node creates a client for connecting to the WaveSpeed AI API.

Stillfront/WaveSpeed · 0 entradas · 1 parámetro · 1 salida

SFWaveSpeedFluxControlNetUnionPro2

Flux ControlNet Union Pro 2.0 Node Advanced ControlNet model supporting simultaneous Canny, Depth, Soft Edge, Pose, and Grayscale conditioning for precise image generation control.

Stillfront/WaveSpeed · 1 salida

SFWaveSpeedFluxKontextDev

Flux Kontext Dev Node Advanced image-to-image transformation model for style conversion. Specializes in converting images to anime style and other artistic transformations. Built on Flux architecture with enhanced context understanding.

Stillfront/WaveSpeed · 2 entradas · 7 parámetros · 1 salida

SFWaveSpeedFluxKontextMax

Flux Kontext Max Node Maximum capability image-to-image transformation model with advanced safety controls. Top-tier version of Flux Kontext featuring enhanced performance and configurable safety tolerance for professional content creation workflows.

Stillfront/WaveSpeed · 2 entradas · 4 parámetros · 1 salida

SFWaveSpeedFluxKontextPro

Flux Kontext Pro Node Professional-grade image-to-image transformation model optimized for production use. Streamlined version of Flux Kontext with simplified parameters and enhanced performance. Ideal for consistent, high-quality image transformations with minimal configuration.

Stillfront/WaveSpeed · 2 entradas · 3 parámetros · 1 salida

SFWaveSpeedImageUpscaler

WaveSpeed AI Image Upscaler Node The AI image upscaler is a powerful tool designed to enhance the resolution and quality of images. Our model allows users to choose different levels of enhancement by adjusting the value of creativity.

Stillfront/WaveSpeed · 2 entradas · 4 parámetros · 1 salida

SFWaveSpeedInfiniteTalk

WaveSpeed AI InfiniteTalk Node Audio-driven conversational AI video generation model that creates talking or singing videos from a single image and audio input. Features accurate lip synchronization, head movement alignment, and facial expression matching with the audio. Unlike traditional dubbing methods, InfiniteTalk enables infinite-length video generation with consistent identity preservation and instruction following capabilities.

Stillfront/WaveSpeed · 4 entradas · 5 parámetros · 1 salida

SFWaveSpeedInfiniteTalkMulti

WaveSpeed AI InfiniteTalk Multi Node Audio-driven multi-character conversational AI video generation model that creates talking or singing videos from a single image and 2 audio inputs. Features accurate lip synchronization, head movement alignment, and multi-character conversation support. Unlike standard InfiniteTalk, this Multi version enables simultaneous multi-character conversations with synchronized audio and movements, perfect for dialogue scenes and multi-person interactions.

Stillfront/WaveSpeed · 5 entradas · 6 parámetros · 1 salida

SFWaveSpeedNanoBananaEdit

Google Nano Banana Edit Node Google's state-of-the-art image generation and editing model

Stillfront/WaveSpeed · 2 entradas · 4 parámetros · 1 salida

SFWaveSpeedNanoBananaProEdit

Google Nano Banana Pro Edit (Gemini 3.0 Pro Image) Advanced AI-powered image editing with 1K/2K/4K resolution support. Combines precision, flexibility, and semantic awareness for professional-grade editing. Features: - Native 4K image generation with fine detail - Natural-language, context-aware editing - Multilingual on-image text with auto translation - Camera-style controls (angle, focus, depth of field) - Consistent character and style rendering - Supports up to 6 input images Pricing: $0.14/image (1k/2k), $0.24/image (4k)

Stillfront/WaveSpeed · 1 salida

SFWaveSpeedNanoBananaProEditMulti

Google Nano Banana Pro Edit Multi (Gemini 3.0 Pro Image) Next-generation multi-image editing model that produces multiple edited outputs from one or more input images in a single run. Features: - True multi-edit generation (multiple variants per request) - Consistent editing style across outputs - Industry-leading cost efficiency at $0.07/image - Precise editing behavior (object replacement, style changes, etc.) - Fast, reliable, no cold starts - Supports up to 6 input images Pricing: $0.07/image

Stillfront/WaveSpeed · 1 salida

SFWaveSpeedNanoBananaProEditUltra

Google Nano Banana Pro Edit Ultra (Gemini 3.0 Pro Image) Ultra high-resolution AI-powered image editing with 4K/8K output support. Combines precision, flexibility, and semantic awareness for professional-grade editing. Features: - Native 4K/8K image generation with fine detail and clean edges - Natural-language, context-aware editing - Multilingual on-image text with auto translation - Camera-style controls (angle, focus, depth of field) - Consistent character and style rendering - Supports up to 6 input images Pricing: $0.15/image (4k), $0.18/image (8k)

Stillfront/WaveSpeed · 1 salida

SFWaveSpeedNanoBananaProTextToImage

Google Nano Banana Pro Text-to-Image (Gemini 3.0 Pro Image) High-quality text-to-image generation with 1K/2K/4K resolution support. Features native 4K generation, multilingual text, and camera-style controls. Pricing: $0.14/image (1k/2k), $0.24/image (4k)

Stillfront/WaveSpeed · 1 salida

SFWaveSpeedNanoBananaProTextToImageMulti

Google Nano Banana Pro Text-to-Image Multi (Gemini 3.0 Pro Image) Generate multiple high-quality images from a single prompt in one run. Extremely cost-effective at only $0.07 per image. Features true multi-image batching, consistent style across outputs, and powerful prompt understanding for editorial-style prompts. Pricing: $0.07/image

Stillfront/WaveSpeed · 1 salida

SFWaveSpeedNanoBananaProTextToImageUltra

Google Nano Banana Pro Text-to-Image Ultra (Gemini 3.0 Pro Image) Ultra high-resolution text-to-image generation with 4K/8K output support. Native 4K/8K image generation with fine detail and clean edges. Features multilingual on-image text, camera-style controls, and consistent character/style rendering. Pricing: $0.15/image (4k), $0.18/image (8k)

Stillfront/WaveSpeed · 1 salida

SFWaveSpeedNanoBananaTextToImage

No hay una descripción breve disponible para este nodo.

Stillfront/WaveSpeed · 1 entrada · 4 parámetros · 1 salida

SFWaveSpeedQwenEdit

Qwen Image Edit Node Qwen-Image-Edit — a 20B MMDiT model for next-gen image edit generation. Built on 20B Qwen-Image, it brings precise bilingual text editing (Chinese & English) while preserving style, and supports both semantic and appearance-level editing.

Stillfront/WaveSpeed · 2 entradas · 4 parámetros · 1 salida

SFWaveSpeedQwenEditLora

Qwen Image Edit with LoRA Node Advanced version of Qwen-Image-Edit that supports LoRA (Low-Rank Adaptation) models for fine-tuned image editing capabilities. Enables more precise control over style and editing behavior through custom LoRA weights.

Stillfront/WaveSpeed · 2 entradas · 8 parámetros · 1 salida

SFWaveSpeedQwenEditPlus

No hay una descripción breve disponible para este nodo.

Stillfront/WaveSpeed · 1 salida

SFWaveSpeedQwenEditPlusLora

No hay una descripción breve disponible para este nodo.

Stillfront/WaveSpeed · 1 salida

SFWaveSpeedQwenTextToImage

Qwen Image Text-to-Image Node Qwen-Image — a 20B MMDiT model for next-gen text-to-image generation.

Stillfront/WaveSpeed · 1 salida

SFWaveSpeedQwenTextToImageLora

Qwen Image Text-to-Image with LoRA Node Advanced version of Qwen-Image text-to-image that supports LoRA (Low-Rank Adaptation) models for fine-tuned generation with specific styles and characteristics.

Stillfront/WaveSpeed · 1 salida

SFWaveSpeedRunwayUpscale

WaveSpeed AI RunwayML Upscale V1 Node Enhanced video upscaling using RunwayML's advanced AI models. Improves video resolution and quality while preserving content integrity.

Stillfront/WaveSpeed · 2 entradas · 1 parámetro · 1 salida

SFWaveSpeedSeedreamV4

No hay una descripción breve disponible para este nodo.

Stillfront/WaveSpeed · 1 salida

SFWaveSpeedSeedreamV4Edit

No hay una descripción breve disponible para este nodo.

Stillfront/WaveSpeed · 1 salida

SFWaveSpeedSeedreamV4EditSequential

No hay una descripción breve disponible para este nodo.

Stillfront/WaveSpeed · 1 salida

SFWaveSpeedSeedreamV4Sequential

No hay una descripción breve disponible para este nodo.

Stillfront/WaveSpeed · 1 salida

SFWaveSpeedSora2ImageToVideo

OpenAI Sora 2 Image-to-Video Node Transforms static images into dynamic videos with physics-aware motion. Preserves image identity, lighting, and composition while adding cinematic camera movements. Pricing: $0.10 per second.

Stillfront/WaveSpeed · 2 entradas · 3 parámetros · 1 salida

SFWaveSpeedSora2ImageToVideoPro

OpenAI Sora 2 Image-to-Video Pro Node Professional-grade image-to-video with higher resolutions (720p/1080p). Preserves image identity, lighting, and composition while generating physics-aware motion. Supports cinematic camera movements and optional synchronized audio.

Stillfront/WaveSpeed · 2 entradas · 4 parámetros · 1 salida

SFWaveSpeedSora2TextToVideo

OpenAI Sora 2 Text-to-Video Node Generates high-quality videos with physics-aware motion and synchronized audio. Features temporal consistency, high-frequency detail preservation, and strong prompt steerability.

Stillfront/WaveSpeed · 1 entrada · 4 parámetros · 1 salida

SFWaveSpeedSora2TextToVideoPro

OpenAI Sora 2 Text-to-Video Pro Node Professional-grade video generation with higher resolutions (up to 1792*1024). Features physics-aware motion, synchronized audio, and cinematic camera techniques.

Stillfront/WaveSpeed · 1 entrada · 4 parámetros · 1 salida

SFWaveSpeedVeo31FastImageToVideo

Google VEO 3.1 Fast Image-to-Video Node Transforms static images into dynamic videos with natural motion. Fast version processes up to 30% faster than standard model. Preserves original image composition while adding cinematic motion.

Stillfront/WaveSpeed · 2 entradas · 8 parámetros · 1 salida

SFWaveSpeedVeo31FastTextToVideo

Google VEO 3.1 Fast Text-to-Video Node Generates cinematic 1080p videos with natural motion and lighting. Processes up to 30% faster than standard model.

Stillfront/WaveSpeed · 1 entrada · 8 parámetros · 1 salida

SFWaveSpeedVeo31ImageToVideo

Google VEO 3.1 Image-to-Video Node Transforms static images into dynamic videos with high-quality motion. Standard model with more detailed generation (~2-3 minutes per 8-second clip). Supports optional ending frame for transition effects.

Stillfront/WaveSpeed · 2 entradas · 9 parámetros · 1 salida

SFWaveSpeedVeo31ReferenceToVideo

Google VEO 3.1 Reference-to-Video Node Generates videos with consistent subject appearance across frames. Supports 1-3 reference images to maintain character/object consistency. Ideal for character-driven narratives and branded content.

Stillfront/WaveSpeed · 2 entradas · 8 parámetros · 1 salida

SFWaveSpeedVeo31TextToVideo

Google VEO 3.1 Text-to-Video Node Generates high-quality cinematic videos at 1080p with advanced motion and lighting. Standard model with more detailed generation (takes ~2-3 minutes per 8-second clip).

Stillfront/WaveSpeed · 1 entrada · 8 parámetros · 1 salida

SFWaveSpeedWan22Animate

No hay una descripción breve disponible para este nodo.

Stillfront/WaveSpeed · 3 entradas · 4 parámetros · 1 salida

SFWaveSpeedWan22I2V720p

WaveSpeed AI Wan 2.2 I2V 720p Node Advanced image-to-video generation model that creates high-quality 720p videos from still images. Features enhanced motion modeling and temporal consistency with support for both short and medium duration outputs.

Stillfront/WaveSpeed · 3 entradas · 5 parámetros · 1 salida

SFWaveSpeedWan25ImageEdit

Alibaba Wan 2.5 Image Edit node Preserves layout and subject structure while implementing high-quality updates based on natural language

Stillfront/WaveSpeed · 1 salida

SFWaveSpeedWan25ImageToVideo

No hay una descripción breve disponible para este nodo.

Stillfront/WaveSpeed · 2 entradas · 8 parámetros · 1 salida

SFWaveSpeedWan25ImageToVideoFast

No hay una descripción breve disponible para este nodo.

Stillfront/WaveSpeed · 2 entradas · 8 parámetros · 1 salida

SFWaveSpeedWan25TextToImage

No hay una descripción breve disponible para este nodo.

Stillfront/WaveSpeed · 1 entrada · 6 parámetros · 1 salida

SFWaveSpeedWan25TextToVideo

No hay una descripción breve disponible para este nodo.

Stillfront/WaveSpeed · 1 entrada · 8 parámetros · 1 salida

SFWaveSpeedWan25TextToVideoFast

No hay una descripción breve disponible para este nodo.

Stillfront/WaveSpeed · 1 entrada · 8 parámetros · 1 salida

WaveSpeedAI Qwen Image Text to Image

No hay una descripción breve disponible para este nodo.

WaveSpeedAI Qwen Image Text to Image LoRA

No hay una descripción breve disponible para este nodo.

WaveSpeedAI_RunwaymlUpscaleV1Node

No hay una descripción breve disponible para este nodo.

WaveSpeedAI_Wan22I2V720pNode

No hay una descripción breve disponible para este nodo.