image-to-video

bytedance

NEW

seedance-v1-pro-i2v-1080p

ByteDance’s Seedance 1.0 is the new SOTA video generation model—outperforming KLING 2.1 with ultra‑fast generation, superior prompt‑following, cinematic multi‑shot coherence, and unmatched motion realism.

text-to-video

bytedance

NEW

seedance-v1-pro-t2v-480p

ByteDance’s Seedance 1.0 is the new SOTA video generation model—outperforming KLING 2.1 with ultra‑fast generation, superior prompt‑following, cinematic multi‑shot coherence, and unmatched motion realism.

image-to-video

bytedance

NEW

seedance-v1-pro-i2v-720p

ByteDance’s Seedance 1.0 is the new SOTA video generation model—outperforming KLING 2.1 with ultra‑fast generation, superior prompt‑following, cinematic multi‑shot coherence, and unmatched motion realism.

text-to-image

wavespeed-ai

flux-dev-lora-ultra-fast

Rapid, high-quality image generation with FLUX.1 [dev] and LoRA support for personalized styles and brand-specific outputs, ultra fast !

text-to-image

bytedance

HOT

NEW

seedream-v3

ByteDance Seedream V3 is a state-of-the-art text-to-image model that excels in generating high-quality, photorealistic images with exceptional detail and artistic flair.

image-to-image

wavespeed-ai

HOT

flux-kontext-dev-ultra-fast

FLUX.1 Kontext Ultra Fast [dev] is a development version of the state-of-the-art image editing model that lets you edit images using text prompts. It makes editing intuitive by understanding the relationship between visuals and language, with ultra-fast processing speed.

image-to-video

wavespeed-ai

HOT

wan-2.1/i2v-480p-lora

Wan-2.1 i2v model with LoRA, generate high-quality videos with superior visual quality and motion diversity

image-to-image

wavespeed-ai

HOT

flux-kontext-dev

FLUX.1 Kontext [dev] is a development version of the state-of-the-art image editing model that lets you edit images using text prompts. It makes editing intuitive by understanding the relationship between visuals and language.

image-to-video

wavespeed-ai

HOT

wan-2.1/i2v-720p-lora-ultra-fast

Wan-2.1 i2v model with LoRA, generate high-quality videos with superior visual quality and motion diversity

image-to-image

wavespeed-ai

HOT

FAST

flux-kontext-dev/multi-ultra-fast

FLUX.1 Kontext Multi Ultra Fast [dev] is an optimized, high-performance version of the state-of-the-art image editing model that lets you edit multiple images using text prompts. It maintains the same high quality while delivering significantly faster processing times.

image-to-image

wavespeed-ai

HOT

flux-kontext-dev/multi

FLUX.1 Kontext Multi [dev] is a development version of the state-of-the-art image editing model that lets you edit multiple images using text prompts. It makes batch editing intuitive by understanding the relationship between visuals and language.

image-to-video

bytedance

NEW

seedance-v1-pro-i2v-480p

ByteDance’s Seedance 1.0 is the new SOTA video generation model—outperforming KLING 2.1 with ultra‑fast generation, superior prompt‑following, cinematic multi‑shot coherence, and unmatched motion realism.

image-to-image

bytedance

HOT

NEW

portrait

Portrait is a state-of-the-art AI portrait enhancement model that specializes in creating stunning, professional-quality portraits. It intelligently enhances facial features, adjusts skin tones, and optimizes lighting while maintaining natural aesthetics.

image-to-image

bytedance

HOT

NEW

seededit-v3

SeedEdit 3.0 is a state-of-the-art image editing model that lets you edit images using text prompts. It makes editing intuitive by understanding the relationship between visuals and language, allowing for precise changes to objects, scenes, and layout without disrupting the composition.

image-to-video

bytedance

NEW

seedance-v1-lite-i2v-480p

ByteDance's Seedance 1.0 Lite is an optimized video generation model offering fast generation, superior prompt‑following, and quality motion realism at an affordable price.

image-to-video

bytedance

NEW

seedance-v1-lite-i2v-720p

ByteDance's Seedance 1.0 Lite is an optimized video generation model offering fast generation, superior prompt‑following, and quality motion realism at an affordable price.

image-to-video

minimax

hailuo-02/standard

Hailuo 02 Standard - MiniMax's next-generation AI video model with 2.5x efficiency improvement, 85% complex instruction response rate, and industry-leading cost-effectiveness for generating high-quality videos.

text-to-image

wavespeed-ai

HOT

flux-dev-lora

Rapid, high-quality image generation with FLUX.1 [dev] and LoRA support for personalized styles and brand-specific outputs

text-to-image

wavespeed-ai

HOT

flux-dev

Flux-dev text to image model, 12 billion parameter rectified flow transformer

text-to-image

wavespeed-ai

HOT

flux-schnell

FLUX.1 [schnell] is fastest image generation model tailored for local development and personal use, a 12 billion parameter rectified flow transformer

image-to-video

minimax

hailuo-02/pro

Hailuo 02 Pro - MiniMax's next-generation AI video model with 2.5x efficiency improvement, 85% complex instruction response rate, and industry-leading cost-effectiveness for generating high-quality 6-second videos.

text-to-video

google

NEW

veo3

Sound on: Google’s flagship Veo 3 text to video model, with audio

text-to-image

wavespeed-ai

flux-dev-ultra-fast

Flux-dev text to image model, 12 billion parameter rectified flow transformer, ultra fast!

text-to-image

wavespeed-ai

HOT

flux-schnell-lora

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.

image-to-image

wavespeed-ai

NEW

instant-character

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

image-to-image

wavespeed-ai

flux-redux-pro

FLUX.1 Redux [pro] 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.

image-to-image

wavespeed-ai

flux-redux-dev

Open-weight image variation model. Create new versions while preserving key elements of your original.

image-to-video

wavespeed-ai

HOT

wan-2.1/i2v-480p

The Wan2.1 14B model is an advanced image-to-video model that offers accelerated inference capabilities, enabling high-res video generation with high visual quality and motion diversity

image-to-video

wavespeed-ai

HOT

wan-2.1/i2v-720p

Wan2.1 I2V-14B model is capable of generating 720P high-definition videos from images

image-to-video

wavespeed-ai

HOT

wan-2.1/i2v-720p-lora

Wan-2.1 i2v model with LoRA, generate high-quality videos with superior visual quality and motion diversity

image-to-video

wavespeed-ai

HOT

wan-2.1/i2v-720p-ultra-fast

Wan2.1 I2V-14B model is capable of generating 720P high-definition videos from images

image-to-video

wavespeed-ai

HOT

wan-2.1/i2v-480p-ultra-fast

The Wan2.1 14B model is an advanced image-to-video model that offers accelerated inference capabilities, enabling high-res video generation with high visual quality and motion diversity

image-to-image

wavespeed-ai

HOT

flux-kontext-dev-lora

FLUX.1 Kontext LoRA [dev] is a development version of the state-of-the-art image editing model that lets you edit images using text prompts and LoRA models. It makes editing intuitive by understanding the relationship between visuals and language, with support for custom styles through LoRA models.

image-to-image

wavespeed-ai

HOT

FAST

flux-kontext-dev-lora-ultra-fast

FLUX.1 Kontext LoRA Ultra Fast [dev] is an optimized, high-performance version of the state-of-the-art image editing model that lets you edit images using text prompts and LoRA models. It maintains the same high quality while delivering significantly faster processing times.

image-to-video

minimax

video-02

Hailuo 02 - MiniMax's next-generation AI video model with 2.5x efficiency improvement, 85% complex instruction response rate, and industry-leading cost-effectiveness for generating high-quality 6-second videos.

image-to-video

kwaivgi

NEW

kling-v2.1-i2v-pro

Kling 2.1 Pro is an advanced endpoint for the Kling 2.1 model, offering professional-grade videos with enhanced visual fidelity, precise camera movements, and dynamic motion control, perfect for cinematic storytelling.

image-to-image

wavespeed-ai

NEW

flux-kontext-pro/multi

Experimental version of FLUX.1 Kontext [pro] with multi image handling capabilities

image-to-image

wavespeed-ai

NEW

flux-kontext-pro

A state-of-the-art image editing model, Flux Kontext, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini2 Flash.

text-to-image

kwaivgi

NEW

kling-v2.0-i2v-master

Kling AI is a powerful AI Text to Video and Image to Video model family developed by Kuaishou, the company behind one of China’s largest video-sharing platforms.

image-to-video

kwaivgi

kling-v1.6-i2v-pro

Generate 5s videos in 1080p resolution from image

image-to-video

minimax

video-01

Generate 6-second videos with prompts or images (also known as Hailuo). Use the T2V-01 model to create a video with images and text.

image-to-video

kwaivgi

NEW

kling-v2.1-i2v-master

Kling 2.1 Master: The premium endpoint for Kling 2.1, designed for top-tier image-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.

text-to-image

wavespeed-ai

NEW

flux-kontext-max/text-to-image

FLUX.1 Kontext [max] text-to-image is a new premium model brings maximum performance across all aspects – greatly improved prompt adherence.

image-to-image

wavespeed-ai

flux-kontext-max/multi

Experimental version of FLUX.1 Kontext [max] with multi image handling capabilities

image-to-image

wavespeed-ai

NEW

flux-kontext-max

A state-of-the-art image editing model, Flux Kontext, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini2 Flash.

video-to-video

wavespeed-ai

NEW

video-upscaler

The Upscale Model API is a powerful tool designed to enhance the resolution and quality of videos. Whether you're working with low-resolution videos that need a boost or aiming to improve the clarity of existing footage, this API leverages advanced machine learning models to deliver high-quality, upscaled videos.

image-to-video

wavespeed-ai

NEW

wan-2.1-14b-vace

VACE is an all-in-one model designed for video creation and editing. It encompasses various tasks, including reference-to-video generation (R2V), video-to-video editing (V2V), and masked video-to-video editing (MV2V), allowing users to compose these tasks freely. This functionality enables users to explore diverse possibilities and streamlines their workflows effectively, offering a range of capabilities, such as Move-Anything, Swap-Anything, Reference-Anything, Expand-Anything, Animate-Anything, and more.

image-to-video

kwaivgi

NEW

kling-v2.1-i2v-standard

Kling 2.1 Standard is a cost-efficient endpoint for the Kling 2.1 model, delivering high-quality image-to-video generation

text-to-image

wavespeed-ai

NEW

flux-kontext-pro/text-to-image

The FLUX.1 Kontext [pro] text-to-image delivers state-of-the-art image generation results with unprecedented prompt following, photorealistic rendering, and flawless typography.

text-to-video

kwaivgi

NEW

kling-v2.0-t2v-master

Kling AI is a powerful AI Text to Video and Image to Video model family developed by Kuaishou, the company behind one of China’s largest video-sharing platforms.

video-to-video

wavespeed-ai

NEW

wan-2.1/v2v-480p

Inference for Wan 2.1 14B. Unleashing high-res 480p video-to-video prowess with cutting-edge suite of video foundation models

image-to-video

wavespeed-ai

NEW

hunyuan-custom-ref2v-720p

HunyuanCustom, a multi-modal, conditional, and controllable generation model centered on subject consistency, built upon the Hunyuan Video generation framework. It enables the generation of subject-consistent videos conditioned on text, images, audio, and video inputs.

image-to-video

vidu

NEW

start-end-to-video-2.0

Create dynamic videos using just the first and last frame images, enhanced with text descriptions for seamless storytelling.

image-to-image

wavespeed-ai

NEW

hidream-e1-full

HiDream-E1 is an image editing model built on HiDream-I1.

image-to-video

wavespeed-ai

NEW

wan-flf2v

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

text-to-image

wavespeed-ai

hidream-i1-dev

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

text-to-image

wavespeed-ai

hidream-i1-full

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

training

wavespeed-ai

NEW

wan-2.1-14b-lora-trainer

To train a WAN Lora, you need at least 10 images to achieve good results. The trainer outputs a Lora URL, which is a temporary storage URL that is valid for 7 days. You should download the Lora to your own storage.

training

wavespeed-ai

NEW

flux-dev-lora-trainer

A FLUX dev LoRA trainer for subjects and styles.

image-to-image

wavespeed-ai

uno

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

text-to-audio

wavespeed-ai

dia-tts

Dia directly generates realistic dialogue from transcripts. Audio conditioning enables emotion control. Produces natural nonverbals like laughter and throat clearing. will cost $0.04 per 1000 character.

video-to-video

wavespeed-ai

NEW

mmaudio-v2

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

image-to-image

wavespeed-ai

flux-fill-dev

FLUX.1 [dev] Fill 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.

image-to-image

wavespeed-ai

flux-controlnet-union-pro-2.0

FLUX.1 ControlNet Union Pro 2.0 is a high-performance endpoint for the FLUX.1 model with advanced ControlNet capabilities, supporting multiple control modes including Canny, Depth, Pose, and more for precise image generation and control."

text-to-video

wavespeed-ai

wan-2.1/t2v-480p-lora

Turbo-charged inference for Wan 2.1 14B. Unleashing high-res 480p text-to-video prowess with cutting-edge suite of video foundation models, LoRA effect added

text-to-video

wavespeed-ai

wan-2.1/t2v-720p-lora

Turbo-charged inference for Wan 2.1 14B. Unleashing high-res 720p text-to-video prowess with cutting-edge suite of video foundation models, LoRA effect added

text-to-video

wavespeed-ai

wan-2.1/t2v-480p

The Wan2.1 14B model is an advanced text-to-video model that offers accelerated inference capabilities, enabling high-res video generation with high visual quality and motion diversity

text-to-video

bytedance

seedance-v1-lite-t2v-1080p

ByteDance's Seedance 1.0 Lite is an optimized video generation model offering fast generation, superior prompt‑following, and quality motion realism at an affordable price.

text-to-video

bytedance

seedance-v1-lite-t2v-720p

ByteDance's Seedance 1.0 Lite is an optimized video generation model offering fast generation, superior prompt‑following, and quality motion realism at an affordable price.

image-to-video

bytedance

seedance-v1-lite-i2v-1080p

ByteDance's Seedance 1.0 Lite is an optimized video generation model offering fast generation, superior prompt‑following, and quality motion realism at an affordable price.

text-to-video

bytedance

seedance-v1-lite-t2v-480p

ByteDance's Seedance 1.0 Lite is an optimized video generation model offering fast generation, superior prompt‑following, and quality motion realism at an affordable price.

video-effects

video-effects

NEW

blueprint-supreme

Transform your photos into supreme blueprint-style videos with optional background music.

video-effects

video-effects

NEW

FLYING

flying

Transform your photos into superhero-style flying videos with dynamic camera movement.

video-effects

video-effects

NEW

balloon-flyaway

Transform your photos into playful balloon videos where subjects float away with a whimsical spin.

video-effects

video-effects

NEW

romantic-lift

Transform your photos into romantic princess carry videos with natural motion and emotion.

video-effects

video-effects

NEW

COUPLE_ARRIVAL

couple-arrival

Create dynamic videos with your AI companion arriving and sharing warm moments.

video-effects

video-effects

NEW

HUGGING

hugging

Transform your photos into dynamic hugging videos with natural motion and emotion.

video-effects

video-effects

NEW

LOVE_DROP

love-drop

Create romantic and heartwarming videos with dynamic interactions between characters.

video-effects

video-effects

NEW

KISSING

kissing

Transform your photos into dynamic kissing videos with natural motion and emotion.

video-effects

video-effects

NEW

kissing-pro

Transform your dual-person photos into dynamic kissing videos with enhanced synchronization and natural motion.

video-effects

video-effects

NEW

french-kiss

Bring your images to life by turning them into dynamic videos that capture your vision and action.

text-to-video

bytedance

seedance-v1-pro-t2v-1080p

Generate 5s or 10s videos in 1080p resolution from text using bytedance Seedance Pro T2V model

text-to-video

bytedance

seedance-v1-pro-t2v-720p

ByteDance’s Seedance 1.0 is the new SOTA video generation model—outperforming KLING 2.1 with ultra‑fast generation, superior prompt‑following, cinematic multi‑shot coherence, and unmatched motion realism.

text-to-video

wavespeed-ai

NEW

veo2-t2v

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

image-to-video

wavespeed-ai

NEW

veo2-i2v

Veo 2 creates videos from images with realistic motion and very high quality output.

text-to-image

wavespeed-ai

NEW

imagen4

Google’s highest quality image generation model

video-to-video

wavespeed-ai

wan-2.1/v2v-720p-lora

Turbo-charged inference for Wan 2.1 14B. Unleashing high-res 720p video-to-video prowess with cutting-edge suite of video foundation models

video-to-video

wavespeed-ai

wan-2.1/v2v-480p-lora

Turbo-charged inference for Wan 2.1 14B. Unleashing high-res 480p video-to-video prowess with cutting-edge suite of video foundation models

video-to-video

wavespeed-ai

wan-2.1/v2v-480p-lora-ultra-fast

Turbo-charged inference for Wan 2.1 14B. Unleashing high-res 720p video-to-video prowess with cutting-edge suite of video foundation models

video-to-video

wavespeed-ai

wan-2.1/v2v-720p-lora-ultra-fast

Turbo-charged inference for Wan 2.1 14B. Unleashing high-res 720p video-to-video prowess with cutting-edge suite of video foundation models

video-to-video

wavespeed-ai

wan-2.1/v2v-720p-ultra-fast

Turbo-charged inference for Wan 2.1 14B. Unleashing high-res 720p video-to-video prowess with cutting-edge suite of video foundation models

video-to-video

wavespeed-ai

wan-2.1/v2v-720p

Inference for Wan 2.1 14B. Unleashing high-res 720p video-to-video prowess with cutting-edge suite of video foundation models

video-to-video

wavespeed-ai

wan-2.1/v2v-480p-ultra-fast

Turbo-charged inference for Wan 2.1 14B. Unleashing high-res 480p video-to-video prowess with cutting-edge suite of video foundation models

image-to-video

wavespeed-ai

NEW

FEATURED

hunyuan-custom-ref2v-480p

HunyuanCustom, a multi-modal, conditional, and controllable generation model centered on subject consistency, built upon the Hunyuan Video generation framework. It enables the generation of subject-consistent videos conditioned on text, images, audio, and video inputs.

text-to-image

wavespeed-ai

sdxl-lora

SDXL is a text-to-image generative AI model developed by Stability AI that creates beautiful images. It is the successor to Stable Diffusion.

text-to-image

wavespeed-ai

sdxl

SDXL is a text-to-image generative AI model developed by Stability AI that creates beautiful images. It is the successor to Stable Diffusion.

image-to-video

wavespeed-ai

ltx-video-v097/i2v-720p

Generate videos from prompts and images using LTX Video-0.9.7

image-to-video

wavespeed-ai

ltx-video-v097/i2v-480p

Generate videos from prompts and images using LTX Video-0.9.7

text-to-image

wavespeed-ai

NEW

step1x-edit

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

image-to-video

vidu

NEW

reference-to-video-2.0

Create videos that align with reference subjects—like characters, objects, and environments—using the world’s first Multi-Entity Consistency feature.

image-to-video

vidu

NEW

image-to-video-2.0

Bring your images to life by turning them into dynamic videos that capture your vision and action.

image-to-video

wavespeed-ai

NEW

SkyReels-V1

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

image-to-video

wavespeed-ai

NEW

magi-1-24b

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

image-to-video

wavespeed-ai

NEW

framepack

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

image-to-image

wavespeed-ai

flux-control-lora-depth

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.

image-to-image

wavespeed-ai

flux-control-lora-canny

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.

image-to-image

wavespeed-ai

NEW

real-esrgan

Real-ESRGAN with optional face correction and adjustable upscale

image-to-image

wavespeed-ai

HOT

ghibli

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

image-to-video

wavespeed-ai

hunyuan-video/i2v

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 image and text descriptions.

image-to-video

wavespeed-ai

HOT

wan-2.1/i2v-480p-lora-ultra-fast

Wan-2.1 i2v model with LoRA, generate high-quality videos with superior visual quality and motion diversity

image-to-video

kwaivgi

kling-v1.6-i2v-standard

Generate 5s videos in 720p resolution from image

text-to-video

kwaivgi

kling-v1.6-t2v-standard

Generate 5s videos in 720p resolution

text-to-video

wavespeed-ai

wan-2.1/t2v-720p

Turbo-charged inference for Wan 2.1 14B. Unleashing high-res text-to-video prowess with cutting-edge suite of video foundation models

text-to-video

wavespeed-ai

hunyuan-video/t2v

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.

text-to-video

wavespeed-ai

wan-2.1/t2v-480p-ultra-fast

The Wan2.1 14B model is an advanced text-to-video model that offers accelerated inference capabilities, enabling high-res video generation with high visual quality and motion diversity

text-to-video

wavespeed-ai

wan-2.1/t2v-720p-ultra-fast

Turbo-charged inference for Wan 2.1 14B. Unleashing high-res text-to-video prowess with cutting-edge suite of video foundation models

text-to-video

wavespeed-ai

wan-2.1/t2v-480p-lora-ultra-fast

Turbo-charged inference for Wan 2.1 14B. Unleashing high-res 480p text-to-video prowess with cutting-edge suite of video foundation models, LoRA effect added

text-to-video

wavespeed-ai

wan-2.1/t2v-720p-lora-ultra-fast

Turbo-charged inference for Wan 2.1 14B. Unleashing high-res 720p text-to-video prowess with cutting-edge suite of video foundation models, LoRA effect added

image-to-3d

wavespeed-ai

hunyuan3d-v2-multi-view

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