image-to-video

wavespeed-ai

wan-2.2/i2v-480p

Generate unlimited AI videos with Wan 2.2 A14B image to video model.

image-to-image

bytedance

seedream-v4/edit

Seedream 4.0 is a state-of-art image model by Bytedance. Seedream 4.0: Surpassing Nano Banana in every aspect.

text-to-image

bytedance

seedream-v4

Seedream 4.0 is a state-of-art image model by Bytedance. Seedream 4.0: Surpassing Nano Banana in every aspect.

image-to-video

wavespeed-ai

infinitetalk

InfiniteTalk is an audio-driven conversational AI video generation model. Create talking or singing videos from a single image and audio input. Our endpoint starts with $0.15 per 5 seconds (480p) or $0.3 per 5 seconds (720p) video generation and supports a maximum generation length of 10 minutes.

image-to-image

google

nano-banana/edit

Google's state-of-the-art image generation and editing model

image-to-video

bytedance

seedance-v1-pro-i2v-480p

ByteDance Seedance is an advanced AI video model that excels in coherent multi-shot video generation. It can deliver smooth, stable motion, and accurately follow detailed prompts for complex video content.

image-to-image

bytedance

seedream-v4/edit-sequential

Seedream 4.0, Image Generation with 4K Resolution · Editing · Character & Object Consistency · Multi-Image Generation in Sequence. Price = unit_price * max_images

video-to-video

wavespeed-ai

wan-2.2/fun-control

Wan2.2-Fun-Control is a next-generation video generation and control model launched by Alibaba PAI team. Through innovative Control Codes mechanism combined with deep learning and multi-modal conditional inputs, it can generate high-quality videos that comply with preset control conditions. The model is released under the Apache 2.0 license and supports commercial use. Our endpoint starts with $0.2 per 5 seconds video generation and supports a maximum generation length of 120 seconds.

video-to-audio

wavespeed-ai

hunyuan-video-foley

Upload a video and provide a text description to generate realistic audio.

text-to-image

bytedance

seedream-v4/sequential

Seedream 4.0, Image Generation with 4K Resolution · Editing · Character & Object Consistency · Multi-Image Generation in Sequence. Price = unit_price * max_images

text-to-image

wavespeed-ai

flux-dev-lora

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.

image-to-video

minimax

hailuo-02/i2v-standard

Hailuo 02 is a new AI video generation model, from Hailuo AI, created on MiniMax's evolving framework. It has been fine-tuned to deliver ultra-clear 768P resolution and unprecedented responsiveness while even handling, the craziest of physics driven scenes.

video-to-video

wavespeed-ai

infinitetalk/video-to-video

InfiniteTalk is an audio-driven conversational AI video generation model. Create talking or singing videos from a single image and audio input.Our endpoint starts with $0.15 per 5 seconds (480p) or $0.3 per 5 seconds (720p) video generation and supports a maximum generation length of 10 minutes.

video-to-video

wavespeed-ai

wan-2.2/video-edit

Edit videos with text prompt easily. Powered by Wan 2.2, our endpoint lets you modify the content of your videos as simple as possible. For example, you can use text prompts like "Change her clothing to bikini." or "Change the woman to a handsome boy." to modify the video directly. Our endpoint starts with $0.2 per 5 seconds (480p) or $0.4 per 5 seconds (720p) video generation and supports a maximum generation length of 120 seconds.

image-to-image

wavespeed-ai

qwen-image/edit-lora

Qwen-Image-Edit — a 20B MMDiT model for next-gen image edit generation. Built on 20B Qwen-Image, it brings precise bilingual text editing (Chinese & English) while preserving style, and supports both semantic and appearance-level editing.

image-to-video

kwaivgi

kling-v2.1-i2v-standard

Kling v2.1 is the latest evolution of Kuaishou's AI-powered video‑generation model, designed to seamlessly create short, cinematic‑quality clips (typically 5–10 s at 720p or 1080p) from a single image or a text prompt. It represents a major leap forward from Kling 2.0, emphasizing motion fidelity, visual coherence, and prompt accuracy.

image-to-video

wavespeed-ai

infinitetalk/multi

InfiniteTalk Multi is an audio-driven multi-character conversational AI video generation model. Create talking or singing videos from a single image and 2 audio inputs. Our endpoint starts with $0.15 per 5 seconds (480p) or $0.3 per 5 seconds (720p) video generation and supports a maximum generation length of 10 minutes.

text-to-video

google

veo3-fast

Generate videos with Google Veo 3 Fast - faster and more cost-effective than standard Veo 3. Starting at $0.25/second. Commercial use allowed.

text-to-image

wavespeed-ai

qwen-image/text-to-image-lora

Qwen-Image LoRa — a 20B MMDiT model for next-gen text-to-image generation with LoRA.

video-to-audio

wavespeed-ai

think-sound

Upload a video and provide a text description to generate realistic audio.