ALL VIDEO MODELS
All video models to boost your creativity
WaveSpeedAI hosts both open-source and proprietary video generation models across T2V, I2V, reference-based generation, and editing tasks, include SkyReels, Vidu 2.0, WAN 2.1, Magi-1, and MiniMax Video, Hunyuan, Kling, and Framepack. All powered by WaveSpeedAI’s fast inference engine, enabling real-time generation and API integration.
wavespeed-ai/wan-2.1/i2v-480p
$0.2
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
wavespeed-ai/wan-2.1/i2v-480p-lora
$0.2
Wan-2.1 i2v model with LoRA, generate high-quality videos with superior visual quality and motion diversity
wavespeed-ai/wan-2.1/i2v-720p
$0.3
Wan2.1 I2V-14B model is capable of generating 720P high-definition videos from images
wavespeed-ai/wan-2.1/i2v-720p-lora
$0.3
Wan-2.1 i2v model with LoRA, generate high-quality videos with superior visual quality and motion diversity
wavespeed-ai/wan-2.1/i2v-720p-ultra-fast
$0.225
Wan2.1 I2V-14B model is capable of generating 720P high-definition videos from images
wavespeed-ai/wan-2.1/i2v-480p-ultra-fast
$0.125
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
wavespeed-ai/wan-2.1/i2v-720p-lora-ultra-fast
$0.225
Wan-2.1 i2v model with LoRA, generate high-quality videos with superior visual quality and motion diversity
kwaivgi/kling-v1.6-i2v-pro
$0.49
Generate 5s videos in 1080p resolution from image
minimax/video-01
$0.5
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.
vidu/start-end-to-video-2.0
$0.2
Create dynamic videos using just the first and last frame images, enhanced with text descriptions for seamless storytelling.
wavespeed-ai/wan-flf2v
$0.1
Wan-2.1 flf2v generates dynamic videos by intelligently bridging a given first frame to a desired end frame through smooth, coherent motion sequences.
wavespeed-ai/magi-1-24b
$0.08
MAGI-1 is a video generation model with exceptional understanding of physical interactions and cinematic prompts
wavespeed-ai/framepack
$0.033
Framepack is an efficient Image-to-video model that autoregressively generates videos.
wavespeed-ai/wan-2.1/t2v-480p-lora
$0.2
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
wavespeed-ai/wan-2.1/t2v-720p-lora
$0.3
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
wavespeed-ai/wan-2.1/t2v-480p
$0.2
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
wavespeed-ai/hunyuan-video/i2v
$0.4
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.
wavespeed-ai/wan-2.1/i2v-480p-lora-ultra-fast
$0.125
Wan-2.1 i2v model with LoRA, generate high-quality videos with superior visual quality and motion diversity
wavespeed-ai/hunyuan-video/t2v
$0.4
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.
kwaivgi/kling-v1.6-i2v-standard
$0.28
Generate 5s videos in 720p resolution from image
kwaivgi/kling-v1.6-t2v-standard
$0.28
Generate 5s videos in 720p resolution
wavespeed-ai/SkyReels-V1
$0.2
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
vidu/image-to-video-2.0
$0.2
Bring your images to life by turning them into dynamic videos that capture your vision and action.
vidu/reference-to-video-2.0
$0.2
Create videos that align with reference subjects—like characters, objects, and environments—using the world’s first Multi-Entity Consistency feature.
wavespeed-ai/wan-2.1/t2v-720p
$0.3
Turbo-charged inference for Wan 2.1 14B. Unleashing high-res text-to-video prowess with cutting-edge suite of video foundation models
wavespeed-ai/wan-2.1/t2v-480p-ultra-fast
$0.125
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
wavespeed-ai/wan-2.1/t2v-720p-ultra-fast
$0.225
Turbo-charged inference for Wan 2.1 14B. Unleashing high-res text-to-video prowess with cutting-edge suite of video foundation models
wavespeed-ai/wan-2.1/t2v-480p-lora-ultra-fast
$0.125
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
wavespeed-ai/wan-2.1/t2v-720p-lora-ultra-fast
$0.225
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