Explore AI Models

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

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

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

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

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

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

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

Generate 5s videos in 1080p resolution from image

Generate 6s videos with prompts or images. (Also known as Hailuo). Use a subject reference to make a video with a character and the S2V-01 model.

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.

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.

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.

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

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.

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

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

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.

A FLUX dev LoRA trainer for subjects and styles.

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.

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

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

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

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

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

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

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

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

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

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

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

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

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

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.

Generate videos from prompts and images using LTX Video-0.9.7

Generate videos from prompts and images using LTX Video-0.9.7

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

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

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

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

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

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.

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

Generate 5s videos in 720p resolution from image

Generate 5s videos in 720p resolution

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

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.

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

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

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

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

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