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.

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 video generation (480p) and supports a maximum generation length of 120 seconds.

text-to-image

wavespeed-ai

wan-2.2/text-to-image-lora

Generate super detailed images from text prompts with WAN 2.2, supporting custom LoRAs.

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.

image-to-video

wavespeed-ai

wan-2.2/speech-to-video

Wan-2.2-S2V is a video model that generates high-quality videos from static images and audio, with realistic facial expressions, body movements. Our endpoint starts with $0.15 per 5 seconds video generation (480p) and supports a maximum generation length of 120 seconds.

training

wavespeed-ai

flux-dev-lora-trainer

Train custom FLUX LoRA models 10x faster. Style training, character training, object training. From concept to model in minutes, not hours. Upload a ZIP file containing images to start!

text-to-image

bytedance

seedream-v4/edit

bytedance/seedream-v4/edit

text-to-image

bytedance

seedream-v4/sequential

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

image-edit

alibaba

wan-2.5/image-edit

Refine existing visuals using Alibaba WAN 2.5 image-edit for prompt-driven adjustments and stylistic upgrades.

text-to-image

wavespeed-ai

any-llm

Use any large language model from our selected catalogue

video-to-video

wavespeed-ai

wan-2.2/animate

Wan2.2-Animate is a unified model for character animation and replacement with holistic movement and expression replication. The model is released under the Apache 2.0 license and supports commercial use. Our endpoint starts with $0.25 per 5 seconds (480p) or $0.5 per 5 seconds (720p) video generation and supports a maximum generation length of 120 seconds.

image-to-image

wavespeed-ai

qwen-image/edit-plus

Qwen-Image-Edit-Plus — a 20B MMDiT model for next-gen image edit generation with improved multi-image editing, single-image consistency, and native support for ControlNet.

image-to-image

wavespeed-ai

flux-pulid

FLUX-PuLID combines FLUX.1 [dev] with Personalized User Likeness ID (PuLID) technology, enabling high-quality personalized image generation from reference photos with exceptional realism and custom likenesses.

training

wavespeed-ai

flux-dev-lora-trainer-turbo

Train custom FLUX LoRA models 10x faster. Style training, character training, object training. From concept to model in minutes, not hours. Upload a ZIP file containing images to start!

vision-language

wavespeed-ai

moondream3-preview/point

Locate specific objects in images and get their coordinate points. Moondream3 Point provides precise point localization for computer vision applications.

vision-language

wavespeed-ai

moondream3-preview/detect

Detect objects in images and get precise bounding box coordinates. Moondream3 Detect identifies objects and returns their locations for computer vision applications.

vision-language

wavespeed-ai

moondream3-preview/caption

Generate descriptive captions for images. Moondream3 Caption creates short, normal, or long descriptions to help you understand and describe visual content.

vision-language

wavespeed-ai

moondream3-preview/query

Ask natural language questions about images and get intelligent answers. Moondream3 Query supports visual Q&A with optional chain-of-thought reasoning for detailed explanations.

speech-to-text

wavespeed-ai

openai-whisper-turbo

Instant, accurate speech-to-text powered by Whisper large-v3-turbo. Upload audio and receive multilingual transcripts with automatic language detection and punctuation.

speech-to-text

wavespeed-ai

openai-whisper

Instant, accurate speech-to-text powered by Whisper large-v3-turbo. Upload audio and receive multilingual transcripts with automatic language detection and punctuation.