Transform any text description into detailed, editable 3D models instantly—no CAD skills needed—using advanced generative AI, semantic scene parsing, and multi-view consistent geometry for gaming, design, and rapid prototyping.

Transform 2D images into high-fidelity 3D models instantly using advanced AI—supports photogrammetry, depth mapping, and exports in GLB/OBJ formats for gaming, AR/VR, and design.

Generate full songs from text, lyrics, or melodies with a latent diffusion-powered AI music model offering up to 4:45 min tracks, voice control, and seamless editing.

This endpoint allows clients to extend an existing song / vocal audio track by generating additional material

Audio Inpaint intelligently reconstructs missing or corrupted portions of an audio clip. Whether you need to remove unwanted noises, repair damaged recordings, or fill silent gaps, the model analyzes the surrounding context to generate smooth.

Transform one voice into another in using advanced speech-to-speech technology. Perfect for dubbing, content creation, and voice customization without altering the original message.

Generate up to 30 seconds of professional, royalty-free sound effects from text prompts with customizable duration, looping, and multiple MP3 output formats at 44.1 kHz.

Eleven Music is cleared for nearly all commercial uses, from film and television to podcasts and social media videos, and from advertisements to gaming

The Text-to-Audio endpoint enables you to generate audio by providing a text input along with a valid audio URL or a pre-created voice using a voice_id. The output is an audio file that mimics the sound of the provided audio URL or the selected voice.

The Text-to-Audio endpoint enables you to generate audio by providing a text input along with a valid audio URL or a pre-created voice using a voice_id. The output is an audio file that mimics the sound of the provided audio URL or the selected voice.

Speech-to-Text converts spoken audio into written text, enabling easy transcription for various applications.

The Text-to-Audio endpoint enables you to generate audio by providing a text input along with a valid audio URL or a pre-created voice using a voice_id. The output is an audio file that mimics the sound of the provided audio URL or the selected voice.

The Text-to-Audio endpoint generates audio from text using either a provided audio URL or a voice_id, producing output that mimics the selected voice

Change your voice to sound like someone else—same words, different speaker. Just upload your voice and a target voice.

The Voice Cover endpoint allows you to transform a song or audio file into a celeb/fictional character/singer/politician voice using a proper model id of that character.

The Voice Cover endpoint allows you to transform a song or audio file into a celeb/fictional character/singer/politician voice using a proper model id of that character.

The Song Generator endpoint enables you to generate song by providing a lyrics along with a valid audio URL as reference Prompt [

The Music Generation API allows you to generate music based on textual prompts and optional conditioning melodies.

The SFX endpoint allows you to generate sound effects (SFX) from text prompts. It takes user input in the form of a text prompt to conditionally generate audio effects.

The endpoint enables automatic voice translation of videos from one language to another. It accepts a video file link and various parameters to control the dubbing process.

Speech-to-Text transforms audio into written transcription, allowing spoken language to be converted into text for various applications.

Generate original, genre-specific song lyrics instantly using advanced NLP and machine learning—customize by theme, mood, or language, perfect for musicians and content creators seeking fresh, copyright-free lyrics.

Advanced audio isolation technology removes background noise, delivering clear vocals for professional audio applications.

Enhance video audio with advanced voice isolation, eliminating background noise for professional clarity in music and video production.

Fast, scalable LLM for chat completions with 7B parameters, trained on trillions of tokens, supporting multi-select output and real-time token generation for versatile enterprise workflows.

Runway Gen-4 Image Turbo is an advanced image model that generates and edits visuals from 1–2 input images, with powerful tools for upscaling, adding fine details, and maintaining face consistency.

Seedream 4.0 combines text-to-image, into one powerful multimodal model. It delivers pixel-perfect precision with natural language control, making it ideal for creators who want speed, quality, and flexibility in image generation.

Next-generation image creation and editing model delivering ultra-fast 4K resolution outputs, multi-image reference support, natural language editing, and versatile style transfer for creative workflows.

This endpoint enables you to generate descriptive captions for images. By submitting an image to the endpoint, it analyzes the visual content and returns a concise, human-like caption that summarizes what’s depicted in the image.

Transformer-based image editing model with 20B parameters supports pixel-level and semantic edits, bilingual text modification, style transfer, and multi-image editing up to 1024×1024 resolution.

Open-source 20B-parameter text-to-image model with advanced multimodal diffusion transformer architecture, excelling in high-fidelity text rendering and precise image editing.

Qwen Image-to-Image model is designed for image editing and transformation Images. It allows users to modify existing images through text prompts such as changing objects, adjusting backgrounds, or altering styles.

Remove unwanted objects seamlessly from images with high-resolution inpainting up to 1024x1024 pixels, using automatic mask detection for precise edits.

Interior Mixer is a model that combines different interior objects images and design elements into one unified, realistic image.

Flux 2 Pro is an advanced text-to-image generative model designed for high-precision visual synthesis and professional-grade imaging workflows.

FLUX-2-Max is a premium text-to-image model within the FLUX family, built to deliver exceptional image quality with high realism, fine detail, and strong adherence to user prompts.

Flux 2 Pro Image Editing is a high-performance AI tool that allows you to enhance, modify, and transform images with exceptional accuracy. It delivers seamless object removal, realistic background changes, detailed retouching, and professional-quality.

FLUX.2 [max] is the flagship and most capable generative AI model from Black Forest Labs, designed for professional-grade image generation and editing. It represents the pinnacle of the FLUX.2 model family, offering unmatched visual fidelity, creative con

Flux 2 Dev is a high-performance, developer-focused text-to-image generative model designed for experimentation, customization, and advanced creative workflows.

This model allows you to supply an input image along with a text prompt that describes the modifications you want, and it will generate an updated version that reflects your requested changes.

A distilled version of Z-Image that matches or exceeds leading competitors with only 8 NFEs (Number of Function Evaluations)

Z-Image Turbo Model transform an existing image into a new version using a text prompt, rather than generating a picture from scratch. You upload a source image and then describe how you want it changed

Seedream 4.5 has matured from a “basic tool” into a “reliable production tool”. It delivers a significantly lower failure rate in challenging scenarios such as small faces and fine text. It shifts the user experience from “hoping for luck” to “consistentl

Next-generation image creation and editing model delivering ultra-fast 4K resolution outputs, multi-image reference support, natural language editing, and versatile style transfer for creative workflows.

Next-generation image creation and editing model delivering ultra-fast 4K resolution outputs, multi-image reference support, natural language editing, and versatile style transfer for creative workflows.

Ultra-fast image editing with natural language prompts, preserving character consistency and scene details, supporting pixel-perfect edits and complex transformations in seconds.

Ultra-fast image editing with natural language prompts, preserving character consistency and scene details, supporting pixel-perfect edits and complex transformations in seconds.

Generate high-quality 1024x1024 images in 2.3 seconds with efficient 2.1GB GPU memory use, natural language editing, superior character consistency, and real-time style transfers.

Generate high-quality 1024x1024 images in 2.3 seconds with efficient 2.1GB GPU memory use, natural language editing, superior character consistency, and real-time style transfers.

Text to Image -The Imagen 4 API lets you create high quality images in seconds, using text prompt to guide the generation. Note: Maximum prompt length is 480 tokens.

Generate ultra-realistic, high-resolution (1024×1024 px, upscalable) images from text with advanced lighting, detail, and style control—ideal for photorealistic art, design, and marketing visuals.

Generate high-resolution, ultra-detailed images up to 4K (4096×4096) from text in seconds, with advanced text rendering, multi-reference editing, batch output, and flexible styles—ideal for designers, marketers, and digital artists.

FLUX.1 Kontext [pro] is a model designed for advanced Image Editing. Unlike other models, you don’t need to create complex workflows to achieve this - Flux.1 Kontext [pro] handles it just by writing prompt

Generate high-resolution images with precise stylistic control, up to 1080p, and versatile aspect ratios, ideal for creating consistent visuals in various styles.

The Multiple Face Swap endpoint allows swapping all detected faces in a single image with faces from a target image.

Imagen 3.0 Fast is a speed-optimized version of Google’s text-to-image model that generates high-quality, photorealistic images in seconds. The imagen-3.0-fast-generate-001 variant trades some fine detail for much faster turnaround.

Imagen 4.0 Fast (Preview 06-06) is the speed-optimized version designed for rapid, low-latency image generation. It delivers realistic, high-quality visuals and preview-only feature ideal for prototyping and quick iterations.

Imagen 4.0 Ultra (Preview 06-06) is Google’s highest-fidelity text-to-image model, producing ultra-realistic visuals with precise prompt adherence, person generation, and multiple aspect ratios—ideal for detailed, high-quality imagery.

Imagen 3.0 generates high-quality, photorealistic images from text with improved detail, lighting, and prompt accuracy. The imagen-3.0-generate-001 variant specializes in generating well-composed visuals with reduced artifacts, subtle lighting effects.

FLUX Kontext DEV is an in-context image generation API that lets you create, edit, and transform images using text with high consistency.

Ghibli Art Style API transforms your images into dreamy, hand-drawn visuals inspired by Studio Ghibli’s iconic art style.

Generate a rendered image of a floor plan for a room based on the provided input as well as interior

This endpoint transforms damaged or unattractive exteriors into beautifully restored, visually appealing versions using AI

This endpoint transforms exterior house sketches into realistic photographs based on your prompt as well as interior

Transform your space instantly with advanced AI-powered room decorator—upload any room photo, restyle in 50+ design aesthetics, preview realistic 3D renders, and virtually stage with lifelike furniture—no special hardware, cloud-based

Transform interiors with ultra-realistic images, up to 2048x2048 resolution, and detailed text integration, ideal for designing and visualizing spaces with precision.

The Specific Face Swap lets you swap faces in one image by giving both the original image and the target image.

This endpoint allows you to change the environment scenario to check how house will look in different scenario.

Generate photorealistic and imaginative images from text prompts with advanced detail, inpainting, and image-to-image translation features, ideal for creatives and marketers.

Advanced text-to-image generator with 12B parameters, offering 6x faster generation and superior image quality, ideal for professional design and marketing applications.

Generate high-resolution images up to 4MP with rapid 10-second output, ideal for professional printing and fine art creation.

Generate high-quality images in just 2–4 seconds. From realistic and 3D art to fantasy our realtime model brings your ideas to life instantly.

Flux Text-to-Image is a multilingual AI that transforms text prompts into high-quality images in styles like photorealism, sketches, paintings, 3D renders, and abstract art

Image to Image API generates variations of an input image, turns sketches into realistic images, and can blend two images to create a new output.

ControlNet lets you control image generation using inputs like edges (Canny), depth maps (Depth), human poses (OpenPose), straight lines (MLSD), sketches (Lineart), and even functional QR codes (QRCode) to guide and shape the final output with precision

Face Gen is an AI avatar generator that creates images based on your prompt while maintaining a consistent character using your face, in styles like realistic, anime, 3D, chibi, and comic.

Generate ultra-realistic headshots instantly with advanced image generation and facial optimization, supporting resolutions up to 1024x1024.

Make a POST request to https://modelslab.com/api/v6/image_editing/removebg_mask endpoint. Background Remover is an API that automatically removes the background from any image, making it clean and ready for use in any context.

The Inpainting API modifies specific parts of an image based on prompts—just send the image, mask, and prompt to the endpoint in one request.

Seamlessly remove unwanted objects from photos with advanced AI-powered detection, content-aware fill, shadow reconstruction, and high-resolution support for flawless, natural edits.

QR Code Generator transforms plain QR codes into visually appealing, image-based designs while keeping them fully scannable

Upscales images up to 8x resolution using AI-driven super resolution to enhance detail, remove blur, and preserve sharpness for printing and digital use. Supports PNG, JPEG, WebP, and HEIC formats with fast processing and batch capabilities.

The AI Virtual Try-On API lets users digitally try upper wear, lower wear, and full outfits on their photos in seconds.

Seamlessly expand images with intelligent edge-blending, supporting various aspect ratios and maintaining original detail.

Enhance photo quality and resolution instantly with the Image Enhancer — improve clarity and boost details for high-quality, sharp images.

Fast-train your custom models with optimized pipelines, supporting various image formats, and requiring minimal 16GB VRAM for efficient fine-tuning.

Efficiently train custom Stable Diffusion models with flexible batch sizes, gradient checkpointing, and memory-optimized attention requiring 12-24 GB VRAM for high-quality 512×512 to 1024×1024 image outputs.

LTX-2 Pro Text-to-Video is an advanced AI model that converts text descriptions into high-quality short videos. It can generate cinematic visuals with synchronized audio, such as sound effects and ambience.

LTX-2 Pro Image-to-Video is a powerful AI model that turns a single still image into a dynamic video clip using a text prompt to guide motion, camera moves, and atmosphere

Kling Motion Control is an advanced AI-powered motion transfer system that analyzes movement from a reference video and applies it to a static image, creating realistic image-to-video animations with precise body, gesture, and expression control.

OmniHuman takes a single human image and audio, generating a realistic video with natural lip-sync and expressions.

Lipsync-2-Pro takes an input audio and an input video, then generates a perfectly synchronized output video where the character’s lip movements match the audio with natural precision.

Wan 2.5 is a text-to-video model that generates smooth 5–10s videos in 480p–1080p with smart prompt rewriting and watermarking. In Wan2.5, you can also add auto-generated or custom audio for perfect syn

Generate up to 10-second cinematic 1080p videos from images with synchronized audio, natural motion, multilingual support, and precise camera control for professional-quality content.

Wan 2.6 is an advanced multimodal AI video generation Model that lets you turn static inputs like images (or text) into high-quality dynamic videos using artificial intelligence. It integrates text, images, video, and audio into a single system.

Wan 2.6 supports multiple visual styles, dynamic transitions, and flexible aspect ratios, making it ideal for marketing, social media, storytelling, and creative content generation.

wan2.6-i2v-flash is an image-to-video generation model in the WAN 2.6 series. It takes a single input image (plus optional text prompt and audio) and generates a short video clip with motion and optionally synchronized sound.

Generate ultra-realistic cinematic videos from simple text prompts with smooth camera motion and lifelike physics.

Seedance 1.0 PR0 Lite creates AI videos using a first frame, last frame, and a prompt to animate smooth transitions.

Seedance 1.5 PR0 creates AI videos using a first frame, last frame, and a prompt to animate smooth transitions.

Seedance 1.5 PR0 creates AI videos using a first frame, last frame, and a prompt to animate smooth transitions.

Cinematic text-to-video generator with native audio (dialogue+foley+music), up to 1080p/12s output, millisecond lip-sync, MP4 (H.264) at 48 kHz, fast inference for ads and short films.

Veo 3.1 Fast is Google DeepMind’s quick, text-to-video AI that turns prompts into short, realistic videos with synced audio. It’s built for speed, cinematic motion, and clarity, using advanced multimodal diffusion to generate 720p/1080p clips in seconds

A powerful AI model that transforms written prompts into dynamic, cinematic videos with realistic motion, scenes, and sound. It supports 720p/1080p, 24 FPS, in both 16:9 and 9:16 formats. Despite being in preview, it can be used for real commercial

Veo 3.1 (Image-to-Video) instantly transforms a single image and text prompt into smooth, cinematic video with realistic motion and sound.

Convert static images into dynamic videos with 4K resolution, realistic motion, and cinematic effects, ideal for creators seeking high-quality video content.

Transforms a single image and audio into expressive, full-body human videos with semantic gesture understanding, multi-character support, and dynamic camera control.

Seedance 1.0 Pro Fast is an accelerated, high-quality AI model from ByteDance that transforms a still image and a text prompt into a cinematic video. It offers faster generation and lower costs than the standard Seedance 1.0 Pro.

This Model is used to remove any watermarks present in videos, producing clean, watermark-free outputs.

Kling 2.5 Turbo is a state-of-the-art short‐clip video generation model allowing creators to go from prompt to high-quality 5-10 s cinematic video with good motion and style consistency.

Kling V2.6 makes video creation effortless by converting your written prompts into high-quality, dynamic video scenes.

Kling V2.1 Master is the premium-tier version of the text-to-video Model from KlingAI, designed to turn richly described text prompts into high-quality cinematic video clips.

Kling V2 Master Text-to-Video is a state-of-the-art text-to-video engine aimed at creators who want high-quality, cinematic video drives via text prompts.

Kling V2.1 Image-to-Video is a premium video-generation AI model that takes a static image (your input) plus a descriptive prompt of motion, camera, style etc.

Kling V2.5 Turbo is the latest evolution of Kling’s powerful video-generation Model — a cutting-edge image-to-video AI model designed to turn static visuals into breathtaking, dynamic motion clips in seconds.

Kling V2.1 Master isn’t just an animation model it’s a motion director for your imagination. Every frame reflects professional film grammar, fluid motion, and emotionally resonant depth.

Kling V2 Master brings cinematic storytelling to your fingertips. It’s more than animation — it’s AI-assisted cinematography, turning your static visuals into emotionally engaging motion sequences.

Kling V2.1 Image To Video(Start/ End Frame) is a generative AI video model that takes as input a static images (and optionally a prompt) and produces a short video where the input image is animated motion, pan, zoom etc.

MiniMax Hailuo2.3 model is a powerful next-gen text-to-video model aimed at creators who want to turn prompts into short, high-quality video clips with decent resolution and strong motion/physics fidelity.

MiniMax Hailuo2.3 model is a powerful next-gen text-to-video model aimed at creators who want to turn prompts into short, high-quality video clips with decent resolution and strong motion/physics fidelity.

MiniMax Hailuo 2.3 Image-to-Video gives creators a powerful way to transform still images into high-quality dynamic video clips with control over motion, camera and style.

MiniMax Hailuo-2.3 Fast Image-to-Video offers a streamlined, cost-effective and rapid way to animate still images into short video sequences.

MiniMax Hailuo-0.2 Image-to-Video offers a practical and efficient way to animate still images into short videos.

The MiniMax Hailuo-0.2 (Start/End Frame) Image-to-Video variant enables creators to animate still images into dynamic video clips with defined beginning and end visuals.

Kling V1.6 is an advanced generative video model designed to transform multiple input images into coherent, high-quality animated sequences.

Veo 3 Fast by Google is a high-speed AI video generation model that transforms text or image prompts into stunning 1080p videos with native audio. Optimized for quick turnaround, it’s ideal for creators needing rapid, high-quality content production.

Transform your ideas into stunning videos with Seedance AI video generation. Powered by ByteDance's advanced Seedance 1.0 Pro model, generate high-quality videos from image with cinematic camera movements, multi-shot storytelling capability

Edit videos with advanced object manipulation, camera angles, and lighting control using text prompts and optional reference images.

Fast, cost-effective video generation model delivering 10-second cinematic clips in 30 seconds with consistent characters, realistic motion, and multi-aspect ratio support.

veo-3.0-fast-generate-preview is Google’s speed-optimized AI video generation mode that quickly produces 1080p preview videos. It delivers realistic motion, dynamic scenes, and native audio, making it ideal for testing concepts before full-quality renders

Veo 3 by Google is a cutting-edge AI video generation model that creates cinematic, high-quality videos from text or image prompts. With support for dynamic camera movements, detailed storytelling, and resolutions up to 1080p, it’s perfect for creators an

Convert static images into dynamic videos with 4K resolution, realistic motion, and cinematic effects, ideal for creators seeking high-quality video content.

Create stunning cinematic videos from text or images in minutes with a powerful model. Enjoy advanced motion control, 24fps output, and smooth, artifact-free visuals—perfect for filmmakers, creators, and marketers.

Generate high-quality 720p videos at 24fps from images with advanced motion control and seamless transitions, ideal for animations and cinematic outputs.

Achieve flawless lip sync and facial detail in live-action, 3D, and AI videos up to 4K. This advanced model uses diffusion-based super-resolution for realistic results—perfect for dubbing, dialogue replacement, and re-animation.

The Specific Video Swap endpoint lets you replace a selected face in a video using a reference image, while keeping all other faces unchanged.

Multiface Deepfake allows swapping all detected faces in a video with faces from an reference image.

Transform your ideas into stunning videos with Seedance AI video generation. Powered by ByteDance's advanced Seedance 1.0 Pro model, generate high-quality videos from text prompts with cinematic camera movements, multi-shot storytelling capability.

Seedance 1.0 Pro Fast Text-to-Video is a cutting-edge AI model by ByteDance designed to generate high-quality, cinematic video content from text descriptions. This accelerated version of the Seedance 1.0 Pro model emphasizes speed and efficient

Ultra-realistic 4K text-to-video generator with cinematic motion, style control, and up to 8-second clips, perfect for ads, social, and creative storytelling.

Transform text into ultra-realistic HD video instantly, with advanced generative AI, smooth animations, and multi-format export—ideal for marketing, social, and creative projects.

Generate high-quality videos from images with support for up to 4K resolution and cinematic motion, ideal for social media and branding content.

Upload the image, Enter the prompt, and according to prompt video will be created from given image. Support NSFW Generation

Transform text into high-quality video clips with precise control over resolution, frame rate, and style, perfect for social media and marketing content.

Transform any image into dynamic, high-quality short videos (5–6 seconds, 480p/720p, 16 FPS MP4) instantly—ideal for creators, marketers, and rapid content workflows in v6/video/text2video applications.

Entry point for workflow execution - required for every workflow

Exit point for workflow execution - required for every workflow

Add notes and comments to your workflow.

Add a configurable icon to the canvas.

Add a clickable hyperlink to the canvas.