Recraft V3 is a text-to-image model with the ability to generate long texts, vector art, images in brand style, and much more. As of today, it is SOTA in image generation, proven by Hugging Face's industry-leading Text-to-Image Benchmark by Artificial Analysis.

Generate video clips from your images using MiniMax Video model

Generate lip sync using Tavus' state-of-the-art model for high-quality synchronization.

Generate video clips from your prompts using Kling 2.0 Master

HiDream-I1 full is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.

HiDream-I1 dev is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.

HiDream-I1 fast is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within 16 steps.

Add sound effects to your videos

FLUX.1 [dev] is a 12 billion parameter flow transformer that generates high-quality images from text. It is suitable for personal and commercial use.

CassetteAI’s model generates a 30-second sample in under 2 seconds and a full 3-minute track in under 10 seconds. At 44.1 kHz stereo audio, expect a level of professional consistency with no breaks, no squeaks, and no random interruptions in your creations.

MMAudio generates synchronized audio given video and/or text inputs. It can be combined with video models to get videos with audio.

Generate high-quality images, posters, and logos with Ideogram V2. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.

FLUX LoRA training optimized for portrait generation, with bright highlights, excellent prompt following and highly detailed results.

Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.

Super fast endpoint for the FLUX.1 [dev] inpainting model with LoRA support, enabling rapid and high-quality image inpaingting using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.

A versatile endpoint for the FLUX.1 [dev] model that supports multiple AI extensions including LoRA, ControlNet conditioning, and IP-Adapter integration, enabling comprehensive control over image generation through various guidance methods.

Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.

FLUX.1 Image-to-Image is a high-performance endpoint for the FLUX.1 [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Upscale your images with AuraSR.

Clarity upscaler for upscaling images with high very fidelity.

It takes human image animation to a whole new level! It's basically built on this cracked DiT model called Wan2.1-14B-I2V that makes your still pics move in ways that actually look legit.

Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.

Generate videos from prompts, images, and videos using LTX Video-0.9.7 and custom LoRA

Generate videos from prompts and images using LTX Video-0.9.7 and custom LoRA

Generate videos from prompts using LTX Video-0.9.7 and custom LoRA

HunyuanCustom revolutionizes video generation with unmatched identity consistency across multiple input types. Its innovative fusion modules and alignment networks outperform competitors, maintaining subject integrity while responding flexibly to text, image, audio, and video conditions.

Framepack is an efficient Image-to-video model that autoregressively generates videos.

Extend the beginning or end of provided audio with lyrics and/or style using ACE-Step

Modify a portion of provided audio with lyrics and/or style using ACE-Step

Generate music from a lyrics and example audio using ACE-Step

Generate music from a simple prompt using ACE-Step

Rembg-enhance is optimized for 2D vector images, 3D graphics, and photos by leveraging matting technology.

Vidu Q1 Start-End to Video generates smooth transition 1080p videos between specified start and end images.

Vidu Q1 Text to Video generates high-quality 1080p videos with exceptional visual quality and motion diversity

Vidu Q1 Image to Video generates high-quality 1080p videos with exceptional visual quality and motion diversity from a single image

Generate music with lyrics from text using ACE-Step

Enhances a given raster image using the 'creative upscale' tool, increasing image resolution, making the image sharper and cleaner.

Enhances a given raster image using 'crisp upscale' tool, boosting resolution with a focus on refining small details and faces.

Recraft V3 Create Style is capable of creating unique styles for Recraft V3 based on your images.

Recraft V3 is a text-to-image model with the ability to generate long texts, vector art, images in brand style, and much more. As of today, it is SOTA in image generation, proven by Hugging Face's industry-leading Text-to-Image Benchmark by Artificial Analysis.

Extend videos with prompts and videos using LTX Video-0.9.6

Create scenes with one or two people using just selfies and text prompt (without LoRAs)

Clone a voice from a sample audio and generate speech from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality text-to-speech.

Generate fast speech from text prompts and different voices using the MiniMax Speech-02 Turbo model, which leverages advanced AI techniques to create high-quality text-to-speech.

Generate videos from prompts, images, and videos using LTX Video-0.9.7

Generate speech from text prompts and different voices using the MiniMax Speech-02 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.

Generate videos from prompts using LTX Video-0.9.7

Generate videos from prompts and images using LTX Video-0.9.7

Generate images from text and a reference image using MiniMax Image-01 for consistent character appearance.

Generate high quality images from text prompts using MiniMax Image-01. Longer text prompts will result in better quality images.

HiDream-I1 full is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.

Generate 3D models from multiple images using Trellis. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Extend existing images with Ideogram V3's reframe feature. Create expanded versions and adaptations while preserving main image and adding new creative directions through prompt guidance.

Generate high-quality images, posters, and logos with Ideogram V3. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.

Replace backgrounds existing images with Ideogram V3's replace background feature. Create variations and adaptations while preserving core elements and adding new creative directions through prompt guidance.

Reimagine existing images with Ideogram V3's remix feature. Create variations and adaptations while preserving core elements and adding new creative directions through prompt guidance.

Transform existing images with Ideogram V3's editing capabilities. Modify, adjust, and refine images while maintaining high fidelity and realistic outputs with precise prompt control.

Edit images with natural language

F Lite is a 10B parameter diffusion model created by Fal and Freepik, trained exclusively on copyright-safe and SFW content.

F Lite is a 10B parameter diffusion model created by Fal and Freepik, trained exclusively on copyright-safe and SFW content. This is a high texture density variant of the model.

Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.

Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.

Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.

Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.

Step1X-Edit transforms your photos with simple instructions into stunning, professional-quality edits—rivaling top proprietary tools.

Image2SVG transforms raster images into clean vector graphics, preserving visual quality while enabling scalable, customizable SVG outputs with precise control over detail levels.

An AI model that transforms input images into new ones based on text prompts, blending reference visuals with your creative directions.

OpenAI's latest image generation and editing model: gpt-1-image. Currently powered with bring-your-own-key.

OpenAI's latest image generation and editing model: gpt-1-image. Currently powered with bring-your-own-key.

MAGI-1 extends videos with an exceptional understanding of physical interactions and prompts

MAGI-1 is a video generation model with exceptional understanding of physical interactions and cinematic prompts

MAGI-1 generates videos from images with exceptional understanding of physical interactions and prompting

Generate high quality video clips with different effects using PixVerse v4

MAGI-1 distilled extends videos faster with an exceptional understanding of physical interactions and prompts

MAGI-1 distilled generates videos faster from images with exceptional understanding of physical interactions and prompting

Clone dialog voices from a sample audio and generate dialogs from text prompts using the Dia TTS which leverages advanced AI techniques to create high-quality text-to-speech.

Framepack is an efficient Image-to-video model that autoregressively generates videos.

Dia directly generates realistic dialogue from transcripts. Audio conditioning enables emotion control. Produces natural nonverbals like laughter and throat clearing.

MAGI-1 distilled is a faster video generation model with exceptional understanding of physical interactions and cinematic prompts

An open source, community-driven and native audio turn detection model by Pipecat AI.

Juggernaut Base Flux LoRA Inpainting by RunDiffusion is a drop-in replacement for Flux [Dev] inpainting that delivers sharper details, richer colors, and enhanced realism to all your LoRAs and LyCORIS with full compatibility.

FASHN v1.5 delivers precise virtual try-on capabilities, accurately rendering garment details like text and patterns at 576x864 resolution from both on-model and flat-lay photo references.

Turn any image into a cute plushie!

InstantCharacter creates high-quality, consistent characters from text prompts, supporting diverse poses, styles, and appearances with strong identity control.

Wan-2.1 flf2v generates dynamic videos by intelligently bridging a given first frame to a desired end frame through smooth, coherent motion sequences.

A blazing fast FLUX dev LoRA trainer for subjects and styles.

Framepack is an efficient Image-to-video model that autoregressively generates videos.

Transform images into 3D cartoon artwork using an AI model that applies cartoon stylization while preserving the original image's composition and details.

Vace a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.

Finegrain Eraser removes any object selected with a mask—along with its shadows, reflections, and lighting artifacts—seamlessly reconstructing the scene with contextually accurate content.

Finegrain Eraser removes any object selected with a bounding box—along with its shadows, reflections, and lighting artifacts—seamlessly reconstructing the scene with contextually accurate content.

Finegrain Eraser removes objects—along with their shadows, reflections, and lighting artifacts—using only natural language, seamlessly filling the scene with contextually accurate content.

Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.

Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.

Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.

Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.

Create stunningly realistic sound effects in seconds - CassetteAI's Sound Effects Model generates high-quality SFX up to 30 seconds long in just 1 second of processing time

Generate realistic lipsync animations from audio using advanced algorithms for high-quality synchronization with Sync Lipsync 2.0 model

AI vectorization model that transforms raster images into scalable SVG graphics, preserving visual details while enabling infinite scaling and easy editing capabilities.

Generate fast high quality video clips from text and image prompts using PixVerse v4

Generate high quality video clips from text and image prompts using PixVerse v4

Generate high quality video clips with different effects using PixVerse v3.5

Generate high quality video clips from text and image prompts using PixVerse v4

Create seamless transition between images using PixVerse v3.5

Generate high quality and fast video clips from text and image prompts using PixVerse v4 fast

Reimagine and transform your ordinary photos into enchanting Studio Ghibli style artwork

Orpheus TTS is a state-of-the-art, Llama-based Speech-LLM designed for high-quality, empathetic text-to-speech generation. This model has been finetuned to deliver human-level speech synthesis, achieving exceptional clarity, expressiveness, and real-time performances.

Sana Sprint is a text-to-image model capable of generating 4K images with exceptional speed.

Sana v1.5 4.8B is a powerful text-to-image model that generates ultra-high quality 4K images with remarkable detail.

Sana v1.5 1.6B is a lightweight text-to-image model that delivers 4K image generation with impressive efficiency.

Kling LipSync is an audio-to-video model that generates realistic lip movements from audio input.

Kling LipSync is a text-to-video model that generates realistic lip movements from text input.

LatentSync is a video-to-video model that generates lip sync animations from audio using advanced algorithms for high-quality synchronization.

Add custom LoRAs to Wan-2.1 is a text-to-video model that generates high-quality videos with high visual quality and motion diversity from images

Train custom LoRAs for Wan-2.1

Fix low resolution images with fast speed and quality of thera.

An advanced dehaze model to remove atmospheric haze, restoring clarity and detail in images through intelligent neural network processing.

Gemini Flash Edit is a model that can edit single image using a text prompt and a reference image.

Gemini Flash Edit Multi Image is a model that can edit multiple images using a text prompt and a reference image.

Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Ray2 Flash is a fast video generative model capable of creating realistic visuals with natural, coherent motion.

Ray2 Flash is a fast video generative model capable of creating realistic visuals with natural, coherent motion.

Pika v2.1 creates videos from images with high quality output.

Pika v2.2 creates videos from images with high quality output.

Pika v2 Turbo creates videos from a text prompt with high quality output.

Pika v2.2 creates videos from a text prompt with high quality output.

Pika Scenes v2.2 creates videos from a images with high quality output.

Pika Effects are AI-powered video effects designed to modify objects, characters, and environments in a fun, engaging, and visually compelling manner.

Pika v2.1 creates videos from a text prompt with high quality output.

Invisible Watermark is a model that can add an invisible watermark to an image.

Pika v2 Turbo creates videos from images with high quality output.

CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs.

Vidu Template to Video lets you create different effects by applying motion templates to your images.

Vidu Image to Video generates high-quality videos with exceptional visual quality and motion diversity from a single image

Vidu Start-End to Video generates smooth transition videos between specified start and end images.

Vidu Reference to Video creates videos by using a reference images and combining them with a prompt.

Wan-2.1 Pro is a premium text-to-video model that generates high-quality 1080p videos at 30fps with up to 6 seconds duration, delivering exceptional visual quality and motion diversity from text prompts

Swap faces of one or two people at once, while preserving user and scene details!

Generate video clips from your prompts using Kling 1.6 (std)

Generate video clips from your prompts using Kling 1.5 (pro)

Generate video clips from your prompts using Kling 1.0

Generate video clips from your prompts using Kling 1.6 (pro)

Image to Video for the high-quality Hunyuan Video I2V model.

Generate videos from prompts using LTX Video-0.9.5

Generate videos from prompts,images, and videos using LTX Video-0.9.5

Generate videos from prompts and images using LTX Video-0.9.5

Juggernaut Pro Flux by RunDiffusion is the flagship Juggernaut model rivaling some of the most advanced image models available, often surpassing them in realism. It combines Juggernaut Base with RunDiffusion Photo and features enhancements like reduced background blurriness.

Juggernaut Pro Flux by RunDiffusion is the flagship Juggernaut model rivaling some of the most advanced image models available, often surpassing them in realism. It combines Juggernaut Base with RunDiffusion Photo and features enhancements like reduced background blurriness.

Juggernaut Base Flux by RunDiffusion is a drop-in replacement for Flux [Dev] that delivers sharper details, richer colors, and enhanced realism, while instantly boosting LoRAs and LyCORIS with full compatibility.

Juggernaut Lightning Flux by RunDiffusion provides blazing-fast, high-quality images rendered at five times the speed of Flux. Perfect for mood boards and mass ideation, this model excels in both realism and prompt adherence.

RunDiffusion Photo Flux provides insane realism. With this enhancer, textures and skin details burst to life, turning your favorite prompts into vivid, lifelike creations. Recommended to keep it at 0.65 to 0.80 weight. Supports resolutions up to 1536x1536.

Juggernaut Base Flux LoRA by RunDiffusion is a drop-in replacement for Flux [Dev] that delivers sharper details, richer colors, and enhanced realism to all your LoRAs and LyCORIS with full compatibility.

Juggernaut Base Flux by RunDiffusion is a drop-in replacement for Flux [Dev] that delivers sharper details, richer colors, and enhanced realism, while instantly boosting LoRAs and LyCORIS with full compatibility.

Generate videos from prompts and videos using LTX Video-0.9.5

Generate high quality images from text prompts using CogView4. Longer text prompts will result in better quality images.

DiffRhythm is a blazing fast model for transforming lyrics into full songs. It boasts the capability to generate full songs in less than 30 seconds.

Professional-grade video upscaling using Topaz technology. Enhance your videos with high-quality upscaling.

Enhance low-resolution, blur, shadowed documents with the superior quality of docres for sharper, clearer results.

Enhance wraped, folded documents with the superior quality of docres for sharper, clearer results.

Enhance low-resolution images with the superior quality of Swin2SR for sharper, clearer results.

Wan-2.1 1.3B is a text-to-video model that generates high-quality videos with high visual quality and motion diversity from text promptsat faster speeds.

Generate video clips from your prompts using Kling 1.6 (pro)

Rapidly create image variations with Ideogram V2A Turbo Remix. Fast and efficient reimagining of existing images while maintaining creative control through prompt guidance.

Isolate audio tracks using ElevenLabs advanced audio isolation technology.

Generate sound effects using ElevenLabs advanced sound effects model.

Create variations of existing images with Ideogram V2A Remix while maintaining creative control through prompt guidance.

Generate high-speed text-to-speech audio using ElevenLabs TTS Turbo v2.5.

Accelerated image generation with Ideogram V2A Turbo. Create high-quality visuals, posters, and logos with enhanced speed while maintaining Ideogram's signature quality.

Generate high-quality images, posters, and logos with Ideogram V2A. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.

Generate multilingual text-to-speech audio using ElevenLabs TTS Multilingual v2.

Generate text from speech using ElevenLabs advanced speech-to-text model.

EVF-SAM2 combines natural language understanding with advanced segmentation capabilities, allowing you to precisely mask image regions using intuitive positive and negative text prompts.

Bring colors into old or new black and white photos with DDColor.

Wan-2.1 is a text-to-video model that generates high-quality videos with high visual quality and motion diversity from text prompts

Generate video prompts using a variety of techniques including camera direction, style, pacing, special effects and more.

SAM 2 is a model for segmenting images automatically. It can return individual masks or a single mask for the entire image.

Upscale your images with DRCT-Super-Resolution.

Generate video clips more accurately with respect to initial image, natural language descriptions, and using camera movement instructions for shot control.

Veo 2 creates videos with realistic motion and high quality output. Explore different styles and find your own with extensive camera controls.

Use NAFNet to fix issues like blurriness and noise in your images. This model specializes in image restoration and can help enhance the overall quality of your photography.

Use NAFNet to fix issues like blurriness and noise in your images. This model specializes in image restoration and can help enhance the overall quality of your photography.

Post Processing is an endpoint that can enhance images using a variety of techniques including grain, blur, sharpen, and more.

SkyReels V1 is the first and most advanced open-source human-centric video foundation model. By fine-tuning HunyuanVideo on O(10M) high-quality film and television clips

Clone voice of any person and speak anything in their voice using zonos' voice cloning.

A natural and expressive Brazilian Portuguese text-to-speech model optimized for clarity and fluency.

A fast and natural-sounding Japanese text-to-speech model optimized for smooth pronunciation.

A natural-sounding Spanish text-to-speech model optimized for Latin American and European Spanish.

Kokoro is a lightweight text-to-speech model that delivers comparable quality to larger models while being significantly faster and more cost-efficient.

A high-quality Italian text-to-speech model delivering smooth and expressive speech synthesis.

A high-quality British English text-to-speech model offering natural and expressive voice synthesis.

A highly efficient Mandarin Chinese text-to-speech model that captures natural tones and prosody.

A fast and expressive Hindi text-to-speech model with clear pronunciation and accurate intonation.

An expressive and natural French text-to-speech model for both European and Canadian French.

Ray2 is a large-scale video generative model capable of creating realistic visuals with natural, coherent motion.

The model provides you high quality image editing capabilities.

GOT-OCR2 works on a wide range of tasks, including plain document OCR, scene text OCR, formatted document OCR, and even OCR for tables, charts, mathematical formulas, geometric shapes, molecular formulas and sheet music.

FLUX Control LoRA Canny is a high-performance endpoint that uses a control image using a Canny edge map to transfer structure to the generated image and another initial image to guide color.

A fast and high quality model for image background removal.

FLUX Control LoRA Depth is a high-performance endpoint that uses a control image using a depth map to transfer structure to the generated image and another initial image to guide color.

FLUX Control LoRA Depth is a high-performance endpoint that uses a control image to transfer structure to the generated image, using a depth map.

FLUX Control LoRA Canny is a high-performance endpoint that uses a control image to transfer structure to the generated image, using a Canny edge map.

A model for high quality and smooth background removal for videos.

Generate video clips more accurately with respect to natural language descriptions and using camera movement instructions for shot control.

Imagen3 is a high-quality text-to-image model that generates realistic images from text prompts.

Ideogram Upscale enhances the resolution of the reference image by up to 2X and might enhance the reference image too. Optionally refine outputs with a prompt for guided improvements.

Imagen3 Fast is a high-quality text-to-image model that generates realistic images from text prompts.

Image to Video for the Hunyuan Video model using a custom trained LoRA.

Lumina-Image-2.0 is a 2 billion parameter flow-based diffusion transforer which features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.

Fix distorted or blurred photos of people with CodeFormer.

Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability. Use this endpoint to generate videos from videos.

Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability. Use this endpoint to generate videos from videos.

Generate high quality video clips from text prompts using PixVerse v3.5

Generate high quality video clips from text and image prompts quickly using PixVerse v3.5 Fast

Generate high quality video clips quickly from text prompts using PixVerse v3.5 Fast

Generate high quality video clips from text and image prompts using PixVerse v3.5

YuE is a groundbreaking series of open-source foundation models designed for music generation, specifically for transforming lyrics into full songs.

DeepSeek Janus-Pro is a novel text-to-image model that unifies multimodal understanding and generation through an autoregressive framework

Ray2 is a large-scale video generative model capable of creating realistic visuals with natural, coherent motion.

Kling Kolors Virtual TryOn v1.5 is a high quality image based Try-On endpoint which can be used for commercial try on.

Compose videos from multiple media sources using FFmpeg API.

Get encoding metadata from video and audio files using FFmpeg API.

Get waveform data from audio files using FFmpeg API.

Generate video clips maintaining consistent, realistic facial features and identity across dynamic video content

MoonDreamNext Batch is a multimodal vision-language model for batch captioning.

FLUX1.1 [pro] is an enhanced version of FLUX.1 [pro], improved image generation capabilities, delivering superior composition, detail, and artistic fidelity compared to its predecessor.

Utilize Flux.1 [dev] Controlnet to generate high-quality images with precise control over composition, style, and structure through advanced edge detection and guidance mechanisms.

Utilize Flux.1 [pro] Controlnet with a fine-tuned LoRA to generate high-quality images with precise control over composition, style, and structure through advanced edge detection and guidance mechanisms.

FLUX1.1 [pro] ultra fine-tuned is the newest version of FLUX1.1 [pro] with a fine-tuned LoRA, maintaining professional-grade image quality while delivering up to 2K resolution with improved photo realism.

Generate high-quality images from depth maps using Flux.1 [pro] depth estimation model. The model produces accurate depth representations for scene understanding and 3D visualization.

FLUX.1 [pro] Fill Fine-tuned is a high-performance endpoint for the FLUX.1 [pro] model with a fine-tuned LoRA that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability

FLUX LoRA for Pro endpoints.

Utilize Flux.1 [pro] Controlnet to generate high-quality images with precise control over composition, style, and structure through advanced edge detection and guidance mechanisms.

Generate high-quality images from depth maps using Flux.1 [pro] depth estimation model with a fine-tuned LoRA. The model produces accurate depth representations for scene understanding and 3D visualization.

Transform text into stunning videos with TransPixar - an AI model that generates both RGB footage and alpha channels, enabling seamless compositing and creative video effects.

Train Hunyuan Video lora on people, objects, characters and more!

Generate videos from prompts using CogVideoX-5B

Multimodal vision-language model for single/multi image understanding

Generate realistic lipsync animations from audio using advanced algorithms for high-quality synchronization.

Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels

Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels

Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels

Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels

MoonDreamNext Detection is a multimodal vision-language model for gaze detection, bbox detection, point detection, and more.

MoonDreamNext is a multimodal vision-language model for captioning, gaze detection, bbox detection, point detection, and more.

Generate video clips from your images using Kling 1.6 (std)

Generate video clips from your prompts using Kling 1.6 (std)

Automatically generates text captions for your videos from the audio as per text colour/font specifications

Switti is a scale-wise transformer for fast text-to-image generation that outperforms existing T2I AR models and competes with state-of-the-art T2I diffusion models while being faster than distilled diffusion models.

Switti is a scale-wise transformer for fast text-to-image generation that outperforms existing T2I AR models and competes with state-of-the-art T2I diffusion models while being faster than distilled diffusion models.

This endpoint delivers seamlessly localized videos by generating lip-synced dubs in multiple languages, ensuring natural and immersive multilingual experiences

Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

MMAudio generates synchronized audio given text inputs. It can generate sounds described by a prompt.

Bria RMBG 2.0 enables seamless removal of backgrounds from images, ideal for professional editing tasks. Trained exclusively on licensed data for safe and risk-free commercial use. Model weights for commercial use are available here: https://share-eu1.hsforms.com/2GLpEVQqJTI2Lj7AMYwgfIwf4e04

Bria Background Replace allows for efficient swapping of backgrounds in images via text prompts or reference image, delivering realistic and polished results. Trained exclusively on licensed data for safe and risk-free commercial use

Blazing-fast text-to-speech. Generate audio with improved emotional tones and extensive multilingual support. Ideal for high-volume processing and efficient workflows.

Bria's Text-to-Image model, trained exclusively on licensed data for safe and risk-free commercial use. Available also as source code and weights. For access to weights: https://bria.ai/contact-us

Place any product in any scenery with just a prompt or reference image while maintaining high integrity of the product. Trained exclusively on licensed data for safe and risk-free commercial use and optimized for eCommerce.

Bria Eraser enables precise removal of unwanted objects from images while maintaining high-quality outputs. Trained exclusively on licensed data for safe and risk-free commercial use. Access the model's source code and weights: https://bria.ai/contact-us

Bria's Text-to-Image model for HD images. Trained exclusively on licensed data for safe and risk-free commercial use. Available also as source code and weights. For access to weights: https://bria.ai/contact-us

FLUX.1 [dev] Fill is a high-performance endpoint for the FLUX.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Bria GenFill enables high-quality object addition or visual transformation. Trained exclusively on licensed data for safe and risk-free commercial use. Access the model's source code and weights: https://bria.ai/contact-us

Bria Expand expands images beyond their borders in high quality. Trained exclusively on licensed data for safe and risk-free commercial use. Access the model's source code and weights: https://bria.ai/contact-us

Bria's Text-to-Image model with perfect harmony of latency and quality. Trained exclusively on licensed data for safe and risk-free commercial use. Available also as source code and weights. For access to weights: https://bria.ai/contact-us

Image based high quality Virtual Try-On

Leffa Pose Transfer is an endpoint for changing pose of an image with a reference image.

Generate music from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality, diverse musical compositions.

Leffa Virtual TryOn is a high quality image based Try-On endpoint which can be used for commercial try on.

Generate video clips from your prompts using MiniMax model

Rodin by Hyper3D generates realistic and production ready 3D models from text or images.

Generate video clips from your images using MiniMax Video model

Recraft 20b is a new and affordable text-to-image model.

Transform existing images with Ideogram V2's editing capabilities. Modify, adjust, and refine images while maintaining high fidelity and realistic outputs with precise prompt control.

Generate 3D models from your images using Trellis. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Generate video clips from your prompts using Luma Dream Machine v1.5

FASHN delivers precise virtual try-on capabilities, accurately rendering garment details like text and patterns at 576x864 resolution from both on-model and flat-lay photo references.

The video upscaler endpoint uses RealESRGAN on each frame of the input video to upscale the video to a higher resolution.

Reimagine existing images with Ideogram V2's remix feature. Create variations and adaptations while preserving core elements and adding new creative directions through prompt guidance.

Edit images faster with Ideogram V2 Turbo. Quick modifications and adjustments while preserving the high-quality standards and realistic outputs of Ideogram.

Rapidly create image variations with Ideogram V2 Turbo Remix. Fast and efficient reimagining of existing images while maintaining creative control through prompt guidance.

Accelerated image generation with Ideogram V2 Turbo. Create high-quality visuals, posters, and logos with enhanced speed while maintaining Ideogram's signature quality.

Generate video clips from your prompts using Kling 1.0

Generate images from your prompts using Luma Photon Flash. Photon Flash is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation.

AuraFlow v0.3 is an open-source flow-based text-to-image generation model that achieves state-of-the-art results on GenEval. The model is currently in beta.

OmniGen is a unified image generation model that can generate a wide range of images from multi-modal prompts. It can be used for various tasks such as Image Editing, Personalized Image Generation, Virtual Try-On, Multi Person Generation and more!

FLUX.1 [schnell] Redux is a high-performance endpoint for the FLUX.1 [schnell] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Generate video clips from your prompts using Kling 1.5 (pro)

FLUX.1 [schnell] is a 12 billion parameter flow transformer that generates high-quality images from text in 1 to 4 steps, suitable for personal and commercial use.

FLUX.1 [pro] Redux is a high-performance endpoint for the FLUX.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Generate high-quality images from depth maps using Flux.1 [dev] depth estimation model. The model produces accurate depth representations for scene understanding and 3D visualization.

FLUX.1 [dev] Redux is a high-performance endpoint for the FLUX.1 [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Generate videos from images using LTX Video

FLUX.1 [pro] Fill is a high-performance endpoint for the FLUX.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

FLUX1.1 [pro] Redux is a high-performance endpoint for the FLUX1.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

FLUX1.1 [pro] ultra Redux is a high-performance endpoint for the FLUX1.1 [pro] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

Photorealistic Image-to-Image

An endpoint for re-lighting photos and changing their backgrounds per a given description

Mochi 1 preview is an open state-of-the-art video generation model with high-fidelity motion and strong prompt adherence in preliminary evaluation.

FLUX.1 Differential Diffusion is a rapid endpoint that enables swift, granular control over image transformations through change maps, delivering fast and precise region-specific modifications while maintaining FLUX.1 [dev]'s high-quality output.

An endpoint for personalized image generation using Flux as per given description.

bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)

Stable Diffusion 3.5 Medium is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.

Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability. This endpoint generates videos from text descriptions.

F5 TTS

Generate videos from videos and prompts using CogVideoX-5B

Generate videos from images and prompts using CogVideoX-5B

Use any vision language model from our selected catalogue (powered by OpenRouter)

Generate video clips from your images using Kling 1.5 (pro)

Generate video clips from your prompts using Kling 1.0 (pro)

Generate videos from prompts using LTX Video

Generate video clips from your images using Kling 1.0

Generate video clips from your images using Kling 1.0 (pro)

FLUX.1 [pro] new is an accelerated version of FLUX.1 [pro], maintaining professional-grade image quality while delivering significantly faster generation speeds.

Transfer expression from a video to a portrait.

A general purpose endpoint for the FLUX.1 [dev] model, implementing the RF-Inversion pipeline. This can be used to edit a reference image based on a prompt.

Generate short video clips from your images using SVD v1.1

Holistically-Nested Edge Detection (HED) preprocessor.

TEED (Temporal Edge Enhancement Detection) preprocessor.

Line art preprocessor.

Generate short video clips from your prompts using SVD v1.1

Depth Anything v2 preprocessor.

Segment Anything Model (SAM) preprocessor.

MiDaS depth estimation preprocessor.

ZoeDepth preprocessor.

M-LSD line segment detection preprocessor.

PIDI (Pidinet) preprocessor.

Scribble preprocessor.

Animate a reference image with a driving video using ControlNeXt.

Multimodal vision-language model for video understanding

Stable Diffusion 3 Medium (Text to Image) is a Multimodal Diffusion Transformer (MMDiT) model that improves image quality, typography, prompt understanding, and efficiency.

SAM 2 is a model for segmenting images and videos in real-time.

SAM 2 is a model for segmenting images and videos in real-time.

FLUX General Inpainting is a versatile endpoint that enables precise image editing and completion, supporting multiple AI extensions including LoRA, ControlNet, and IP-Adapter for enhanced control over inpainting results and sophisticated image modifications.

FLUX General Image-to-Image is a versatile endpoint that transforms existing images with support for LoRA, ControlNet, and IP-Adapter extensions, enabling precise control over style transfer, modifications, and artistic variations through multiple guidance methods.

FLUX LoRA Image-to-Image is a high-performance endpoint that transforms existing images using FLUX models, leveraging LoRA adaptations to enable rapid and precise image style transfer, modifications, and artistic variations.

A specialized FLUX endpoint combining differential diffusion control with LoRA, ControlNet, and IP-Adapter support, enabling precise, region-specific image transformations through customizable change maps.

Default parameters with automated optimizations and quality improvements.

Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, with the ability to generate 4K images in less than a second.

Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Super fast endpoint for the FLUX.1 [schnell] model with subject input capabilities, enabling rapid and high-quality image generation for personalization, specific styles, brand identities, and product-specific outputs.

An efficent SDXL multi-controlnet text-to-image model.

An efficent SDXL multi-controlnet inpainting model.

An efficent SDXL multi-controlnet image-to-image model.

Photorealistic Text-to-Image

Interpolate between image frames

Transfer expression from a video to a portrait.

A powerful image to novel multiview model with normals.

Stable Cascade: Image generation on a smaller & cheaper latent space.

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Run SDXL at the speed of light

Stable Diffusion 3 Medium (Image to Image) is a Multimodal Diffusion Transformer (MMDiT) model that improves image quality, typography, prompt understanding, and efficiency.

Anime finetune of Würstchen V3.

Generate images from your prompts using Luma Photon. Photon is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation.

Generate video clips from your images using Luma Dream Machine v1.5

Generate short video clips from your images using SVD v1.1 at Lightning Speed

Predict poses.

SD 1.5 ControlNet

SOTA Image Upscaler

State-of-the-art open-source model in aesthetic quality

Hyper-charge SDXL's performance and creativity.

Hyper-charge SDXL's performance and creativity.

Generate realistic images.

Collection of SDXL Lightning models.

Dreamshaper model.

Any pose, any style, any identity

High quality zero-shot personalization

Run Any Stable Diffusion model with customizable LoRA weights.

Run Any Stable Diffusion model with customizable LoRA weights.

Stable Diffusion v1.5

Run SDXL at the speed of light

Run SDXL at the speed of light

SDXL with an alpha channel.

Run SDXL at the speed of light

Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

MuseTalk is a real-time high quality audio-driven lip-syncing model. Use MuseTalk to animate a face with your own audio.

[Experimental] Whisper v3 Large -- but optimized by our inference wizards. Same WER, double the performance!

Predict the probability of an image being NSFW.

Answer questions from the images.

Fooocus extreme speed mode as a standalone app.

Create stickers from faces.

Customizing Realistic Human Photos via Stacked ID Embedding

Generate short video clips from your prompts

Generate Images with ControlNet.

Create creative upscaled images.

bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)

Re-animate your videos with evolved consistency!

Interpolate between video frames

State-of-the-art open-source model in aesthetic quality

Run SDXL at the speed of light

Animate your ideas!

State-of-the-art open-source model in aesthetic quality

Hyper-charge SDXL's performance and creativity.

Run SDXL at the speed of light

Whisper is a model for speech transcription and translation.

Run SDXL at the speed of light

Run SDXL at the speed of light

Run SDXL at the speed of light

Fooocus extreme speed mode as a standalone app.

Use any large language model from our selected catalogue (powered by OpenRouter)

Vision

Create depth maps using Midas depth estimation.

Default parameters with automated optimizations and quality improvements.

Re-animate your videos in lightning speed!

Re-animate your videos with evolved consistency!

Generate short video clips from your images using SVD v1.1 at Lightning Speed

Animate your ideas in lightning speed!

Generate video clips from your prompts using MiniMax model

Create illusions conditioned on image.

Default parameters with automated optimizations and quality improvements.

Re-animate your videos!

Automatically retouches faces to smooth skin and remove blemishes.

Produce high-quality images with minimal inference steps.

State of the art Image to 3D Object generation

Diffusion based high quality edge detection

Open source text-to-audio model.

Create depth maps using Marigold depth estimation.

Tuning-free ID customization.

Generate Images with ControlNet.

Generate Images with ControlNet.

Default parameters with automated optimizations and quality improvements.

Animate Your Drawings with Latent Consistency Models!

Produce high-quality images with minimal inference steps. Optimized for 512x512 input image size.

Inpaint images with SD and SDXL

Upscale images by a given factor.

Remove the background from an image.

Run Any Stable Diffusion model with customizable LoRA weights.