# Crun API

## Docs

- [AI Image Background Remove API](https://docs.crun.ai/ai-tools/image-background-remove.md): Remove backgrounds from image content.
- [AI Image Upscale API](https://docs.crun.ai/ai-tools/image-upscale.md): High resolution image Upscaler and Enhancer.
- [AI Image Watermark Remove API](https://docs.crun.ai/ai-tools/image-watermark-remove.md): Remove visible text and watermarks from image content.
- [AI Video Enhance API](https://docs.crun.ai/ai-tools/video-enhance.md): AI video quality enhancement for improving clarity, resolution, and visual fidelity.
- [AI Video Watermark Remove API](https://docs.crun.ai/ai-tools/video-watermark-remove.md): Remove visible watermarks from video content.
- [Get Remaining Credits](https://docs.crun.ai/common-api/get-account-credits.md): Check your account remaining credits balance.
- [Getting Started with CURN API](https://docs.crun.ai/index.md): Access a comprehensive collection of state-of-the-art AI models through our unified API platform. Choose from the latest image generation, video creation, and audio models to power your applications.
- [Bytedance DreamActor API](https://docs.crun.ai/models/bytedance/dreamactor.md): Bytedance DreamActor motion imitation model. Generate a video by transferring motion from a reference video to a reference image.
- [Get Task Info](https://docs.crun.ai/models/common/get-task-info.md): Query the status and results of all model generation tasks.
- [Flux 1.1 Pro](https://docs.crun.ai/models/flux/flux-1-1-pro.md): Faster, better FLUX Pro. Text-to-image model with excellent image quality, prompt adherence, and output diversity.
- [Flux 1.1 Pro Ultra](https://docs.crun.ai/models/flux/flux-1-1-pro-ultra.md): FLUX1.1 pro in ultra and raw modes. Images are up to 4 megapixels. Use raw mode for realism.
- [Flux 2 Flex](https://docs.crun.ai/models/flux/flux-2-flex.md): Flux 2 Flex from Black Forest Labs gives you control over the quality-speed trade-off when generating images. Unlike typical text-to-image models that make these decisions for you, Flex lets you adjust how many steps to run and how strongly the model should follow your prompt.
- [Flux 2 Max](https://docs.crun.ai/models/flux/flux-2-max.md): FLUX.2 [max] is the new top-tier image model from Black Forest Labs, pushing image quality, prompt understanding, and editing consistency to the highest level yet.
- [Flux 2 Pro](https://docs.crun.ai/models/flux/flux-2-pro.md): Flux 2 Pro is an image generation and editing model by Black Forest Labs. It creates high-quality images from text prompts and can edit existing images using natural language instructions. The model handles complex text rendering, photorealistic details, and maintains consistent characters or styles…
- [Flux Kontext Max](https://docs.crun.ai/models/flux/flux-kontext-max.md): A premium text-based image editing model that delivers maximum performance and improved typography generation for transforming images through natural language prompts
- [Flux Kontext Pro](https://docs.crun.ai/models/flux/flux-kontext-pro.md): A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language
- [Gemini Omni](https://docs.crun.ai/models/google/gemini-omni.md): Google Gemini Omni is a multimodal video generation and editing model that turns text, images, and video references into cohesive videos with strong scene consistency, world understanding, and natural-language control.
- [Google Image 4](https://docs.crun.ai/models/google/image-4.md): Google's Imagen 4 flagship model, high-quality image generation model.
- [Nano Banana](https://docs.crun.ai/models/google/nano-banana.md): Create text-to-image or image-to-image generation tasks using Google Nano Banana
- [Nano Banana 2](https://docs.crun.ai/models/google/nano-banana-2.md): Nano Banana 2 is Google’s latest image generation model, built on Gemini 3.1 Flash Image. It’s the high-efficiency counterpart to Nano Banana Pro — optimized for speed and high-volume use cases while still producing high-fidelity images.
- [Nano Banana Pro](https://docs.crun.ai/models/google/nano-banana-pro.md): Create text-to-image or image-to-image generation tasks using Google Nano Banana Pro
- [Veo 3.1 Fast - Image to Video](https://docs.crun.ai/models/google/veo-3-1-fast-image-to-video.md): Use the Veo 3.1 Fast image-to-video model to generate dynamic video from static images.
- [Veo 3.1 Fast - Reference to Video](https://docs.crun.ai/models/google/veo-3-1-fast-reference-to-video.md): Use the Veo 3.1 Fast reference-to-video model to generate video from multiple reference images.
- [Veo 3.1 Fast - Text to Video](https://docs.crun.ai/models/google/veo-3-1-fast-text-to-video.md): Use the Veo 3.1 Fast text-to-video model to generate video from text prompt
- [Veo 3.1 - Image to Video](https://docs.crun.ai/models/google/veo-3-1-image-to-video.md): Use the Veo 3.1 image-to-video model to generate dynamic video from static images.
- [Veo 3.1 Lite - Image to Video](https://docs.crun.ai/models/google/veo-3-1-lite-image-to-video.md): Use the Google Veo 3.1 Lite image-to-video API to animate images into high-fidelity 8-second videos with native audio, selectable resolution, and landscape or portrait framing.
- [Veo 3.1 Lite - Text to Video](https://docs.crun.ai/models/google/veo-3-1-lite-text-to-video.md): Use the Google Veo 3.1 Lite text-to-video API to generate high-fidelity 8-second videos with native audio, selectable resolution, and landscape or portrait framing.
- [Veo 3.1 - Text to Video](https://docs.crun.ai/models/google/veo-3-1-text-to-video.md): Use the Veo 3.1 text-to-video model to generate video from text prompt
- [Grok Imagine - Image to Image](https://docs.crun.ai/models/grok-imagine/image-to-image.md): Content generation using grok imagine image-to-image
- [Grok Imagine - Image to Video](https://docs.crun.ai/models/grok-imagine/image-to-video.md): Content generation using grok imagine image-to-video
- [Grok Imagine - Text to Image](https://docs.crun.ai/models/grok-imagine/text-to-image.md): Content generation using grok imagine text-to-image
- [Grok Imagine - Text to Video](https://docs.crun.ai/models/grok-imagine/text-to-video.md): Content generation using grok imagine text-to-video
- [Grok Imagine Video 1.5 Preview API](https://docs.crun.ai/models/grok-imagine/video-1-5-preview.md): Generate short image-guided videos with Grok Imagine Video 1.5 Preview, an xAI preview video model that accepts one reference image, a required prompt, selectable aspect ratios, 480p or 720p output, and 1-15 second durations.
- [HappyHorse 1.0 Image to Video](https://docs.crun.ai/models/happyhorse/image-to-video.md): The HappyHorse Image‑to‑Video model generates physically realistic and smoothly moving videos guided by text descriptions based on the first‑frame image.
- [HappyHorse 1.0 Reference to Video](https://docs.crun.ai/models/happyhorse/reference-to-video.md): The HappyHorse referenceto video generation model supports inputting multiple reference images. It generates a smooth video by fusing main subjects from the images with scene descriptions via text prompts.
- [HappyHorse 1.0 Text to Video](https://docs.crun.ai/models/happyhorse/text-to-video.md): The HappyHorse text‑to‑video model generates physically realistic and smoothly moving video content from input text prompts.
- [HappyHorse 1.0 Video Edit](https://docs.crun.ai/models/happyhorse/video-edit.md): The HappyHorse video editing model supports input videos and reference images, and performs editing tasks such as style transformation and partial replacement in combination with text instructions.
- [Kling Avatar API](https://docs.crun.ai/models/kling/avatar.md): kling-avatar: Turn any portrait into a talking avatar with audio-synchronized lip sync and natural expressions.
- [Kling-v2.1 Video Generation](https://docs.crun.ai/models/kling/v2-1.md): Use Kling v2.1 to generate 5s and 10s videos in 720p and 1080p resolution from a starting image (image-to-video)
- [Kling-v2.1-master Video Generation](https://docs.crun.ai/models/kling/v2-1-master.md): A premium version of Kling v2.1 with superb dynamics and prompt adherence. Generate 1080p 5s and 10s videos from text or an image
- [Kling-v2.5-turbo-pro Video Generation](https://docs.crun.ai/models/kling/v2-5-turbo-pro.md): Kling 2.5 Turbo Pro: Unlock pro-level text-to-video and image-to-video creation with smooth motion, cinematic depth, and remarkable prompt adherence.
- [Kling-v2.6 Video Generation](https://docs.crun.ai/models/kling/v2-6.md): Kling 2.6: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation
- [Kling V2.6 Motion Control API](https://docs.crun.ai/models/kling/v2-6-motion-control.md): Kling-v2.6-motion-control: Enables precise control of character actions and expressions from a reference image.
- [Kling-v3.0 Video Generation](https://docs.crun.ai/models/kling/v3-0.md): Kling Video 3.0: Generate cinematic videos up to 15 seconds with multi-shot control, native audio, and improved consistency.
- [Kling V3.0 Motion Control API](https://docs.crun.ai/models/kling/v3-motion-control.md): Kling 3.0 motion control: transfer motion from a reference video to any character image with improved consistency and quality.
- [Crun Chat Completions API](https://docs.crun.ai/models/llm/chat-completions.md): OpenAI-compatible /chat/completions endpoint for CRUN language models.
- [Crun Anthropic Messages API](https://docs.crun.ai/models/llm/messages.md): Anthropic-compatible /messages endpoint for CRUN language models, supporting Claude-style messages, system prompts, vision content blocks, tools, thinking, and streaming events.
- [OpenAI Compatible LLM](https://docs.crun.ai/models/llm/quickstart.md): Connect CRUN language models through OpenAI-compatible endpoints and reuse the official OpenAI SDK.
- [Crun Responses API](https://docs.crun.ai/models/llm/responses.md): OpenAI-compatible /responses endpoint for CRUN language models, with flexible input, stateful follow-ups, structured outputs, streaming, and tool-ready response items.
- [Hailuo 02 Video Generation](https://docs.crun.ai/models/minimax/hailuo-02.md): Hailuo 2 is a text-to-video and image-to-video model that can make 6s or 10s videos at 768p (standard) or 1080p (pro). It excels at real world physics.
- [Hailuo 2.3 Video Generation](https://docs.crun.ai/models/minimax/hailuo-2-3.md): A high-fidelity video generation model optimized for realistic human motion, cinematic VFX, expressive characters, and strong prompt and style adherence across both text-to-video and image-to-video workflows.
- [OpenAI GPT-Image-1](https://docs.crun.ai/models/openai/gpt-image-1.md): GPT Image 1 is a natively multimodal language model that accepts both text and image inputs, and produces image outputs.
- [OpenAI GPT-Image-1-5](https://docs.crun.ai/models/openai/gpt-image-1-5.md): GPT Image 1.5 is openai latest image generation model, with better instruction following and adherence to prompts.
- [OpenAI GPT-Image-2 API](https://docs.crun.ai/models/openai/gpt-image-2.md): GPT Image 2 is OpenAI's state-of-the-art image generation model. Create and edit images from text with strong instruction following, sharp text rendering, and detailed editing.
- [OpenAI GPT-Image-2 Premium API](https://docs.crun.ai/models/openai/gpt-image-2-premium.md): GPT Image 2 Premium is a premium channel for GPT Image 2, supporting high-quality image generation and editing with up to 14 reference images.
- [OpenAI GPT-Image-2 Stable API](https://docs.crun.ai/models/openai/gpt-image-2-stable.md): The stable channel version of GPT Image 2 offers improved service reliability and supports quality parameters, along with additional optional settings.
- [Crun P Video Avatar API](https://docs.crun.ai/models/prunaai/p-video-avatar.md): Generate talking-head videos from a single portrait image plus either a script or an audio clip. Upload a photo, give it words to say (or audio to lip-sync to), and get back a video of the person speaking.
- [Crun Models APIs](https://docs.crun.ai/models/quickstart.md): Access a comprehensive collection of state-of-the-art AI models through our unified API platform. Choose from the latest image generation, video creation, and audio models to power your applications.
- [Qwen Image - Text to Image](https://docs.crun.ai/models/qwen/qwen-image.md): Qwen-Image - Text-to-Image model is a general-purpose image generation model that supports various artistic styles, and is particularly good at rendering complex text.
- [Qwen Image 2 - Text to Image](https://docs.crun.ai/models/qwen/qwen-image-2.md): A next-generation image generation and editing model from Alibaba's Qwen team. Supports text-to-image and image editing with strong text rendering, especially for Chinese.
- [Qwen Image 2 Pro - Text to Image](https://docs.crun.ai/models/qwen/qwen-image-2-pro.md): The pro version of Qwen Image 2 from Alibaba's Qwen team. Enhanced text rendering, realism, and semantic adherence for high-quality image generation and editing.
- [Qwen Image Edit - Image Editing](https://docs.crun.ai/models/qwen/qwen-image-edit.md): The image generation base model in the Qwen series has made significant progress in complex text rendering and precise image editing.
- [Qwen Image Edit 2 - Image Editing](https://docs.crun.ai/models/qwen/qwen-image-edit-2.md): A next-generation image generation and editing model from Alibaba's Qwen team. Supports text-to-image and image editing with strong text rendering, especially for Chinese.
- [Qwen Image Edit 2 Pro - Image Editing](https://docs.crun.ai/models/qwen/qwen-image-edit-2-pro.md): The pro version of Qwen Image 2 from Alibaba's Qwen team. Enhanced text rendering, realism, and semantic adherence for high-quality image generation and editing.
- [Qwen Image Edit Max - Image Editing](https://docs.crun.ai/models/qwen/qwen-image-edit-max.md): The most powerful version in the qwen edit model series. Supports single-image editing and multi-image fusion.
- [Qwen Image Edit Plus - Image Editing](https://docs.crun.ai/models/qwen/qwen-image-edit-plus.md): A more economical Qwen Edit model. Supports single-image editing and multi-image fusion.
- [Qwen Image Max - Text to Image](https://docs.crun.ai/models/qwen/qwen-image-max.md): Compared with the Plus series, the qwen image generation model Max series has improved the realism and naturalness of images, effectively reducing AI synthesis traces, and performing prominently in aspects such as human texture, texture details, and text rendering.
- [Qwen Image Plus - Text to Image](https://docs.crun.ai/models/qwen/qwen-image-plus.md): Qwen-Image-Plus - Text-to-Image model supports diverse art styles and excels at rendering complex text within images, enabling layout designs that blend text and images.
- [Qwen3 TTS Speech Synthesis API](https://docs.crun.ai/models/qwen/qwen-tts.md): Qwen's speech synthesis model delivers human-like voices with natural expressiveness. It supports multiple languages and dialects, generates multilingual content using a single voice, and automatically adapts tone to handle complex text.
- [Qwen3 TTS Voice Cloning API](https://docs.crun.ai/models/qwen/qwen-tts-voice-cloning.md): Qwen voice cloning API reference, Qwen voice cloning extracts vocal characteristics from a short audio sample and creates a reusable custom voice -- no model training required.
- [Qwen3 TTS Voice Design API](https://docs.crun.ai/models/qwen/qwen-tts-voice-design.md): Qwen3 TTs Voice design creates custom voices from text descriptions. Describe the voice you want -- specifying gender, age, tone, pace, and other traits.
- [Runway Gen4 Aleph](https://docs.crun.ai/models/runway/gen-4-aleph.md): Runway Aleph is an in-context video model that performs comprehensive video editing and transformation tasks on input videos. The model handles object manipulation, scene generation, environmental changes, and visual transformations through text prompts or reference images.
- [Runway Gen4 Turbo](https://docs.crun.ai/models/runway/gen-4-turbo.md): Gen-4 creates fast, controllable and flexible video generation that can seamlessly sit beside live action, animated and VFX content.
- [Seedance 1.0 Pro Fast - Image to Video](https://docs.crun.ai/models/seedance/1-0-pro-fast/image-to-video.md): Transform images into dynamic videos powered by Bytedance’s advanced Seedance 1.0 Pro Fast model
- [Seedance 1.0 Pro Fast - Text to Video](https://docs.crun.ai/models/seedance/1-0-pro-fast/text-to-video.md): High-quality video generation from text descriptions powered by Bytedance’s advanced Seedance 1.0 Pro Fast model
- [Seedance 1.0 Pro - Image to Video](https://docs.crun.ai/models/seedance/1-0-pro/image-to-video.md): Transform images into dynamic videos powered by Bytedance’s advanced Seedance 1.0 Pro model
- [Seedance 1.0 Pro - Text to Video](https://docs.crun.ai/models/seedance/1-0-pro/text-to-video.md): High-quality video generation from text descriptions powered by Bytedance’s advanced Seedance 1.0 Pro model
- [Seedance 1.5 Pro - Image to Video](https://docs.crun.ai/models/seedance/1-5-pro/image-to-video.md): Transform images into dynamic videos powered by Bytedance’s advanced Seedance 1.5 Pro model
- [Seedance 1.5 Pro - Text to Video](https://docs.crun.ai/models/seedance/1-5-pro/text-to-video.md): High-quality video generation from text descriptions powered by Bytedance’s advanced Seedance 1.5 Pro model
- [Seedance 2.0 Fast - Image to Video](https://docs.crun.ai/models/seedance/2-0-fast/image-to-video.md): Transform images into dynamic videos powered by Bytedance's advanced Seedance 2.0 Fast model
- [Seedance 2.0 Fast - Reference to Video](https://docs.crun.ai/models/seedance/2-0-fast/reference-to-video.md): Generate videos from reference images, videos, and audio powered by Bytedance's advanced Seedance 2.0 Fast model
- [Seedance 2.0 Fast - Text to Video](https://docs.crun.ai/models/seedance/2-0-fast/text-to-video.md): High-quality video generation from text descriptions powered by Bytedance's advanced Seedance 2.0 Fast model
- [Seedance 2.0 - Image to Video](https://docs.crun.ai/models/seedance/2-0/image-to-video.md): Transform images into dynamic videos powered by Bytedance's advanced Seedance 2.0 model
- [Seedance 2.0 - Reference to Video](https://docs.crun.ai/models/seedance/2-0/reference-to-video.md): Generate videos from reference images, videos, and audio powered by Bytedance's advanced Seedance 2.0 model
- [Seedance 2.0 - Text to Video](https://docs.crun.ai/models/seedance/2-0/text-to-video.md): High-quality video generation from text descriptions powered by Bytedance's advanced Seedance 2.0 model
- [Seedance Asset Info API](https://docs.crun.ai/models/seedance/asset-info.md): Query the upload status and metadata of a Seedance custom asset
- [Seedance Asset Upload API](https://docs.crun.ai/models/seedance/asset-upload.md): Upload custom image, video, and audio assets for Seedance workflows
- [Seedream 4.0 API](https://docs.crun.ai/models/seedream/seedream-4.0.md): Create text-to-image or image-to-image generation tasks using Seedream 4.0
- [Seedream 4.5 API](https://docs.crun.ai/models/seedream/seedream-4.5.md): Create text-to-image or image-to-image generation tasks using Seedream 4.5
- [Seedream 5.0 API](https://docs.crun.ai/models/seedream/seedream-5.md): Seedream 5.0 is the latest image generation model released by ByteDance. It is the first model equipped with web search capabilities, enabling it to integrate real-time online information and improve the timeliness of image generation.
- [Sora2 Video Generation](https://docs.crun.ai/models/sora2/sora-2.md): Sora-2 is designed for speed and flexibility. It’s ideal for the exploration phase, when you’re experimenting with tone, structure, or visual style and need quick feedback rather than perfect fidelity.
- [Sora2 Pro Video Generation](https://docs.crun.ai/models/sora2/sora-2-pro.md): sora-2-pro produces higher quality results. It’s the better choice when you need production-quality output.
- [Vidu Q2.0 - Image to Video](https://docs.crun.ai/models/vidu/2-0/image-to-video.md): Use the Vidu q2.0 image-to-video model to generate video from image
- [Crun Vidu Lip Sync API](https://docs.crun.ai/models/vidu/lip-sync.md): Replace or dub audio on an existing video with vidu lip sync, audio-driven lip sync. Give it a video and new audio or text, and it re-animates the speaker’s lip movements to match.
- [Vidu Q1 - First Last Frames to Video](https://docs.crun.ai/models/vidu/q1/first-last-frames-to-video.md): Use the Vidu q1 image-to-video model to generate video from first and last frames
- [Vidu Q1 - Image to Video](https://docs.crun.ai/models/vidu/q1/image-to-video.md): Use the Vidu q1 image-to-video model to generate video from image
- [Vidu Q1 - Reference to Video](https://docs.crun.ai/models/vidu/q1/reference-to-video.md): Use the Vidu q1 reference-to-video model to generate video from multiple reference images.
- [Vidu Q1 - Text to Video](https://docs.crun.ai/models/vidu/q1/text-to-video.md): Use the Vidu q1 text-to-video model to generate video from text prompt
- [Vidu Q2 Pro Fast - First Last Frames to Video](https://docs.crun.ai/models/vidu/q2-pro-fast/first-last-frames-to-video.md): Use the Vidu q2 pro fast image-to-video model to generate video from first and last frames
- [Vidu Q2 Pro Fast - Image to Video](https://docs.crun.ai/models/vidu/q2-pro-fast/image-to-video.md): Use the Vidu q2 pro Fast image-to-video model to generate video from image
- [Vidu Q2 Pro - First Last Frames to Video](https://docs.crun.ai/models/vidu/q2-pro/first-last-frames-to-video.md): Use the Vidu q2 pro image-to-video model to generate video from first and last frames
- [Vidu Q2 Pro - Image to Video](https://docs.crun.ai/models/vidu/q2-pro/image-to-video.md): Use the Vidu q2 pro image-to-video model to generate video from image
- [Vidu Q2 Pro - Reference to Video](https://docs.crun.ai/models/vidu/q2-pro/reference-to-video.md): Vidu Q2 Pro supports editing and creating original videos, creating images as reference videos, and creating videos as reference videos.
- [Vidu Q2 Turbo - First Last Frames to Video](https://docs.crun.ai/models/vidu/q2-turbo/first-last-frames-to-video.md): Use the Vidu q2 turbo image-to-video model to generate video from first and last frames
- [Vidu Q2 Turbo - Image to Video](https://docs.crun.ai/models/vidu/q2-turbo/image-to-video.md): Use the Vidu q2 turbo image-to-video model to generate video from image
- [Vidu Q2 - Reference to Video](https://docs.crun.ai/models/vidu/q2/reference-to-video.md): Use the Vidu q2 reference-to-video model to generate video from multiple reference images.
- [Vidu Q2 - Text to Video](https://docs.crun.ai/models/vidu/q2/text-to-video.md): Use the Vidu q2 text-to-video model to generate video from text prompt
- [Vidu Q3 Pro - Image to Video](https://docs.crun.ai/models/vidu/q3-pro/image-to-video.md): Vidu Q3 Pro image to video, Supports generating videos from a single image or the first and last frames.
- [Vidu Q3 Pro - Text to Video](https://docs.crun.ai/models/vidu/q3-pro/text-to-video.md): Vidu Q3 Model: Efficiently generates high-quality audio and video content, making video content more vivid, expressive, and immersive.
- [Vidu Q3 Turbo - Image to Video](https://docs.crun.ai/models/vidu/q3-turbo/image-to-video.md): Vidu Q3 Turbo image to video, Supports generating videos from a single image or the first and last frames.
- [Vidu Q3 Turbo - Text to Video](https://docs.crun.ai/models/vidu/q3-turbo/text-to-video.md): Vidu Q3 Model: Efficiently generates high-quality audio and video content, making video content more vivid, expressive, and immersive.
- [Vidu Q3 - Reference to Video](https://docs.crun.ai/models/vidu/q3/reference-to-video.md): Use Vidu Q3 reference-to-video to generate videos from one or more reference images.
- [Wan2.2 Animate Move](https://docs.crun.ai/models/wan/2-2-animate-move.md): Use Wan2.2 Animate Move to transfer motion from a reference video to a single portrait image.
- [Wan2.2 Animate Replace](https://docs.crun.ai/models/wan/2-2-animate-replace.md): Use Wan2.2 Animate Replace to swap the subject in a reference video with a single portrait image while preserving motion.
- [Wan2.5-preview - Image to Video](https://docs.crun.ai/models/wan/2-5-preview-image-to-video.md): Use the Wan2.5-preview image-to-video model to generate dynamic video from static images.
- [Wan2.5-preview - Text to Video](https://docs.crun.ai/models/wan/2-5-preview-text-to-video.md): Use the Wan2.5-preview text-to-video model to generate dynamic video from text prompt.
- [Wan2.6-Image to Video](https://docs.crun.ai/models/wan/2-6-image-to-video.md): Use the Wan 2.6 image-to-video model to generate dynamic video from static images.
- [Wan2.6-Reference to Video](https://docs.crun.ai/models/wan/2-6-reference-to-video.md): Use the Wan 2.6 reference-to-video model to generate video from reference image or video
- [Wan2.6-Text to Video](https://docs.crun.ai/models/wan/2-6-text-to-video.md): Use the Wan 2.6 text-to-video model to generate video from text prompt
- [Wan 2.7 Image to Video](https://docs.crun.ai/models/wan/2-7-image-to-video.md): Use Wan 2.7 image-to-video to generate video from one or two images.
- [Wan 2.7 Reference to Video](https://docs.crun.ai/models/wan/2-7-reference-to-video.md): Use Wan 2.7 reference-to-video to generate video from reference images or videos.
- [Wan 2.7 Text to Video](https://docs.crun.ai/models/wan/2-7-text-to-video.md): Use Wan 2.7 text-to-video to generate video from a text prompt, with optional audio.
- [Wan 2.7 Video Edit](https://docs.crun.ai/models/wan/2-7-video-edit.md): Use Wan 2.7 video edit to edit an input video with prompt and optional reference images.
- [Wan 2.6 Image](https://docs.crun.ai/models/wan/wan-2-6-image.md): Tongyi wan image model supports image editing and text-to-image generation, offering a wide range of artistic styles and realistic photographic effects to meet diverse creative needs.
- [Wan 2.7 Image](https://docs.crun.ai/models/wan/wan-2-7-image.md): Wan 2.7 Image Generation and Editing Model supports text-to-image, text-to-image, image-to-image , image editing, and multi-image reference generation.
- [Wan 2.7 Image Pro](https://docs.crun.ai/models/wan/wan-2-7-image-pro.md): Generate and edit high-quality images with Alibaba's Wan 2.7 Pro with 4K output, thinking mode, text-to-image, multi-image editing, and image set generation.
- [Z Image Turbo](https://docs.crun.ai/models/z-image/z-image-turbo.md): Tongyi Z-Image is a lightweight text-to-image model that enables fast image generation, supports Chinese and English text rendering, and flexibly adapts to various resolutions and aspect ratios.
- [Suno API: Cover Music](https://docs.crun.ai/suno-api/cover-music.md): Cover music tracks to new styles while preserving their core melody. It integrates Suno's upload feature, and the expected result is to generate tracks in new styles with the original melody unchanged.
- [Suno API: Extend Music](https://docs.crun.ai/suno-api/extend-music.md): Extend or modify existing music by creating a continuation based on a source suno music track.
- [Suno API: Upload Audio Extend](https://docs.crun.ai/suno-api/extend-music-upload.md): Extend music using an uploaded audio file as reference. incorporates Suno's upload feature, with the expected result being longer audio that seamlessly continues the original audio.
- [Suno API: Generate Music](https://docs.crun.ai/suno-api/generate-music.md): Generate AI music using simple text prompts.
- [Suno API: Generate Music Video](https://docs.crun.ai/suno-api/generate-music-video.md): Generate a music video featuring cover art and scrolling lyrics, based on an existing Suno music track.
- [Crun Suno API Quickstart Guide](https://docs.crun.ai/suno-api/quickstart.md): Crun Suno API supports Suno's latest V5 model, enabling music generation in simple or custom modes, sound effects generation, song covers, and audio extension.
- [Suno API: Sounds Generate](https://docs.crun.ai/suno-api/sounds-generate.md): Generate sound effects, ambience, and loopable audio from text prompts.
- [Suno API: Persona Generate](https://docs.crun.ai/suno-api/suno-persona-generate.md): Generate a Suno music persona based on an existing Suno music track.
- [Suno API Task Info](https://docs.crun.ai/suno-api/suno-task-info.md): Query the status and results of Suno music generation tasks.
- [Suno API: Vocal Separation](https://docs.crun.ai/suno-api/vocal-separation.md): Separate clean vocal, accompaniment, or per‑instrument stems from a suno music track.
- [Suno Vocal Separation Task Info](https://docs.crun.ai/suno-api/vocal-separation-task-info.md): Query the status and results of Suno vocal separation tasks.
- [ByteDance AI Effect Template API](https://docs.crun.ai/templates/bytedance-template.md): Generate AI effect template videos with ByteDance templates through Crun's unified task API. Some ByteDance templates are powered by Seedance 2.0 for high-quality motion, visual realism, and controllable video effects.
- [ByteDance AI Effect Template List API](https://docs.crun.ai/templates/bytedance-template-list.md): Query the ByteDance AI effect template catalog through Crun, including template IDs, covers, preview videos, supported resolutions, input requirements, and credits. Some templates are powered by ByteDance Seedance 2.0.
- [Vidu Template API](https://docs.crun.ai/templates/vidu-template.md): Generate videos with Vidu effect templates through the unified Crun task endpoint. The input object keeps the same field structure as the official Vidu template API.
- [Vidu Template List API](https://docs.crun.ai/templates/vidu-template-list.md): Query the full Vidu effect template catalog through Crun, including template IDs, supported options, preview assets, credits, and input instructions.

## OpenAPI Specs

- [wan-2-7-image](https://docs.crun.ai/models/wan/wan-2-7-image.json)
- [wan-2-7-image-pro](https://docs.crun.ai/models/wan/wan-2-7-image-pro.json)
- [2-7-video-edit](https://docs.crun.ai/models/wan/2-7-video-edit.json)
- [2-7-text-to-video](https://docs.crun.ai/models/wan/2-7-text-to-video.json)
- [2-7-reference-to-video](https://docs.crun.ai/models/wan/2-7-reference-to-video.json)
- [2-7-image-to-video](https://docs.crun.ai/models/wan/2-7-image-to-video.json)
- [video-edit](https://docs.crun.ai/models/happyhorse/video-edit.json)
- [text-to-video](https://docs.crun.ai/models/happyhorse/text-to-video.json)
- [reference-to-video](https://docs.crun.ai/models/happyhorse/reference-to-video.json)
- [image-to-video](https://docs.crun.ai/models/happyhorse/image-to-video.json)
- [video-1-5-preview](https://docs.crun.ai/models/grok-imagine/video-1-5-preview.json)
- [veo-3-1-text-to-video](https://docs.crun.ai/models/google/veo-3-1-text-to-video.json)
- [veo-3-1-lite-text-to-video](https://docs.crun.ai/models/google/veo-3-1-lite-text-to-video.json)
- [veo-3-1-lite-image-to-video](https://docs.crun.ai/models/google/veo-3-1-lite-image-to-video.json)
- [veo-3-1-image-to-video](https://docs.crun.ai/models/google/veo-3-1-image-to-video.json)
- [veo-3-1-fast-text-to-video](https://docs.crun.ai/models/google/veo-3-1-fast-text-to-video.json)
- [veo-3-1-fast-reference-to-video](https://docs.crun.ai/models/google/veo-3-1-fast-reference-to-video.json)
- [veo-3-1-fast-image-to-video](https://docs.crun.ai/models/google/veo-3-1-fast-image-to-video.json)
- [video-face-swap](https://docs.crun.ai/ai-tools/face-swap/video-face-swap.json)
- [video-face-swap-multi](https://docs.crun.ai/ai-tools/face-swap/video-face-swap-multi.json)
- [image-face-swap](https://docs.crun.ai/ai-tools/face-swap/image-face-swap.json)
- [image-face-swap-multi](https://docs.crun.ai/ai-tools/face-swap/image-face-swap-multi.json)
- [gif-face-swap](https://docs.crun.ai/ai-tools/face-swap/gif-face-swap.json)
- [gif-face-swap-multi](https://docs.crun.ai/ai-tools/face-swap/gif-face-swap-multi.json)
- [sora-2](https://docs.crun.ai/models/sora2/sora-2.json)
- [sora-2-pro](https://docs.crun.ai/models/sora2/sora-2-pro.json)
- [detect-face-video](https://docs.crun.ai/ai-tools/face-swap/detect-face-video.json)
- [detect-face-result](https://docs.crun.ai/ai-tools/face-swap/detect-face-result.json)
- [detect-face-image](https://docs.crun.ai/ai-tools/face-swap/detect-face-image.json)
- [vidu-template-list](https://docs.crun.ai/templates/vidu-template-list.json)
- [gemini-omni](https://docs.crun.ai/models/google/gemini-omni.json)
- [bytedance-template-list](https://docs.crun.ai/templates/bytedance-template-list.json)
- [bytedance-template](https://docs.crun.ai/templates/bytedance-template.json)
- [first-last-frames-to-video](https://docs.crun.ai/models/vidu/q2-turbo/first-last-frames-to-video.json)
- [lip-sync](https://docs.crun.ai/models/vidu/lip-sync.json)
- [messages](https://docs.crun.ai/models/llm/messages.json)
- [responses](https://docs.crun.ai/models/llm/responses.json)
- [chat-completions](https://docs.crun.ai/models/llm/chat-completions.json)
- [gpt-image-2-premium](https://docs.crun.ai/models/openai/gpt-image-2-premium.json)
- [wan-2-6-image](https://docs.crun.ai/models/wan/wan-2-6-image.json)
- [2-6-text-to-video](https://docs.crun.ai/models/wan/2-6-text-to-video.json)
- [2-6-reference-to-video](https://docs.crun.ai/models/wan/2-6-reference-to-video.json)
- [2-6-image-to-video](https://docs.crun.ai/models/wan/2-6-image-to-video.json)
- [2-5-preview-text-to-video](https://docs.crun.ai/models/wan/2-5-preview-text-to-video.json)
- [2-5-preview-image-to-video](https://docs.crun.ai/models/wan/2-5-preview-image-to-video.json)
- [2-2-animate-replace](https://docs.crun.ai/models/wan/2-2-animate-replace.json)
- [2-2-animate-move](https://docs.crun.ai/models/wan/2-2-animate-move.json)
- [qwen-image](https://docs.crun.ai/models/qwen/qwen-image.json)
- [qwen-image-plus](https://docs.crun.ai/models/qwen/qwen-image-plus.json)
- [qwen-image-max](https://docs.crun.ai/models/qwen/qwen-image-max.json)
- [qwen-image-edit](https://docs.crun.ai/models/qwen/qwen-image-edit.json)
- [qwen-image-edit-plus](https://docs.crun.ai/models/qwen/qwen-image-edit-plus.json)
- [qwen-image-edit-max](https://docs.crun.ai/models/qwen/qwen-image-edit-max.json)
- [qwen-image-edit-2](https://docs.crun.ai/models/qwen/qwen-image-edit-2.json)
- [qwen-image-edit-2-pro](https://docs.crun.ai/models/qwen/qwen-image-edit-2-pro.json)
- [qwen-image-2](https://docs.crun.ai/models/qwen/qwen-image-2.json)
- [qwen-image-2-pro](https://docs.crun.ai/models/qwen/qwen-image-2-pro.json)
- [v3-0](https://docs.crun.ai/models/kling/v3-0.json)
- [z-image-turbo](https://docs.crun.ai/models/z-image/z-image-turbo.json)
- [vidu-template](https://docs.crun.ai/templates/vidu-template.json)
- [video-watermark-remove](https://docs.crun.ai/ai-tools/video-watermark-remove.json)
- [video-enhance](https://docs.crun.ai/ai-tools/video-enhance.json)
- [image-watermark-remove](https://docs.crun.ai/ai-tools/image-watermark-remove.json)
- [image-upscale](https://docs.crun.ai/ai-tools/image-upscale.json)
- [image-background-remove](https://docs.crun.ai/ai-tools/image-background-remove.json)
- [vocal-separation](https://docs.crun.ai/suno-api/vocal-separation.json)
- [vocal-separation-task-info](https://docs.crun.ai/suno-api/vocal-separation-task-info.json)
- [suno-task-info](https://docs.crun.ai/suno-api/suno-task-info.json)
- [suno-persona-generate](https://docs.crun.ai/suno-api/suno-persona-generate.json)
- [sounds-generate](https://docs.crun.ai/suno-api/sounds-generate.json)
- [generate-music](https://docs.crun.ai/suno-api/generate-music.json)
- [generate-music-video](https://docs.crun.ai/suno-api/generate-music-video.json)
- [extend-music](https://docs.crun.ai/suno-api/extend-music.json)
- [extend-music-upload](https://docs.crun.ai/suno-api/extend-music-upload.json)
- [cover-music](https://docs.crun.ai/suno-api/cover-music.json)
- [sora-watermark-remover](https://docs.crun.ai/models/sora2/sora-watermark-remover.json)
- [sora-2-pro-storyboard](https://docs.crun.ai/models/sora2/sora-2-pro-storyboard.json)
- [seedream-5](https://docs.crun.ai/models/seedream/seedream-5.json)
- [seedream-4.5](https://docs.crun.ai/models/seedream/seedream-4.5.json)
- [seedream-4.0](https://docs.crun.ai/models/seedream/seedream-4.0.json)
- [asset-upload](https://docs.crun.ai/models/seedance/asset-upload.json)
- [asset-info](https://docs.crun.ai/models/seedance/asset-info.json)
- [gen-4-turbo](https://docs.crun.ai/models/runway/gen-4-turbo.json)
- [gen-4-aleph](https://docs.crun.ai/models/runway/gen-4-aleph.json)
- [qwen-tts](https://docs.crun.ai/models/qwen/qwen-tts.json)
- [qwen-tts-voice-design](https://docs.crun.ai/models/qwen/qwen-tts-voice-design.json)
- [qwen-tts-voice-cloning](https://docs.crun.ai/models/qwen/qwen-tts-voice-cloning.json)
- [p-video-avatar](https://docs.crun.ai/models/prunaai/p-video-avatar.json)
- [gpt-image-2](https://docs.crun.ai/models/openai/gpt-image-2.json)
- [gpt-image-2-stable](https://docs.crun.ai/models/openai/gpt-image-2-stable.json)
- [gpt-image-1](https://docs.crun.ai/models/openai/gpt-image-1.json)
- [gpt-image-1-5](https://docs.crun.ai/models/openai/gpt-image-1-5.json)
- [hailuo-2-3](https://docs.crun.ai/models/minimax/hailuo-2-3.json)
- [hailuo-02](https://docs.crun.ai/models/minimax/hailuo-02.json)
- [v3-motion-control](https://docs.crun.ai/models/kling/v3-motion-control.json)
- [v2-6](https://docs.crun.ai/models/kling/v2-6.json)
- [v2-6-motion-control](https://docs.crun.ai/models/kling/v2-6-motion-control.json)
- [v2-5-turbo-pro](https://docs.crun.ai/models/kling/v2-5-turbo-pro.json)
- [v2-1](https://docs.crun.ai/models/kling/v2-1.json)
- [v2-1-master](https://docs.crun.ai/models/kling/v2-1-master.json)
- [avatar](https://docs.crun.ai/models/kling/avatar.json)
- [text-to-image](https://docs.crun.ai/models/grok-imagine/text-to-image.json)
- [image-to-image](https://docs.crun.ai/models/grok-imagine/image-to-image.json)
- [nano-banana](https://docs.crun.ai/models/google/nano-banana.json)
- [nano-banana-pro](https://docs.crun.ai/models/google/nano-banana-pro.json)
- [nano-banana-2](https://docs.crun.ai/models/google/nano-banana-2.json)
- [image-4](https://docs.crun.ai/models/google/image-4.json)
- [flux-kontext-pro](https://docs.crun.ai/models/flux/flux-kontext-pro.json)
- [flux-kontext-max](https://docs.crun.ai/models/flux/flux-kontext-max.json)
- [flux-2-pro](https://docs.crun.ai/models/flux/flux-2-pro.json)
- [flux-2-max](https://docs.crun.ai/models/flux/flux-2-max.json)
- [flux-2-flex](https://docs.crun.ai/models/flux/flux-2-flex.json)
- [flux-1-1-pro](https://docs.crun.ai/models/flux/flux-1-1-pro.json)
- [flux-1-1-pro-ultra](https://docs.crun.ai/models/flux/flux-1-1-pro-ultra.json)
- [get-task-info](https://docs.crun.ai/models/common/get-task-info.json)
- [dreamactor](https://docs.crun.ai/models/bytedance/dreamactor.json)
- [get-account-credits](https://docs.crun.ai/common-api/get-account-credits.json)

## Optional

- [Home](https://crun.ai)
- [首页](https://crun.ai/zh)