Seedance 2.5 generates videos from text prompts, allowing customization of duration, resolution, aspect ratio, output format, and optional audio generation. This model supports creating videos up to 30 seconds with flexible visual and audio settings.
HIGGSFIELD API
Sign up for 15% off all sale models - then raise your favorites up to 50%, plus $15 on your balance. Your first result is minutes away
Integration
CONNECT ONCE. BUILD ANYTHING.
1const res = await fetch(2 'https://api.higgsfield.ai/bytedance/seedance-2.0/text-to-video', {3 method: 'POST',4 headers: {5 Authorization: `Key ${HF_API_KEY_ID}:${HF_API_KEY_SECRET}`,6 'Content-Type': 'application/json',7 },8 body: JSON.stringify({9 prompt: 'A cinematic tracking shot along a sunlit coastal road',10 resolution: '720p',11 generate_audio: true,12 duration: 5,13 aspect_ratio: '16:9',14 })15 }16)- Seedance 2.5
- Kling 3.0
- MiniMax H3
- Wan 3.0 Prime
- Marketing Studio Image
- Seedance 2.0
- Grok Imagine 2.0
- Soul 2
- Wan 3.0
- LTX 2.5 Fast
- LTX 2.5 Pro
- Grok Imagine Video 1.5
- Wan 2.7
- Happy Horse 1.1
- Ideogram 4.0
- Recraft 4.1
- Happy Horse 1.0
- PixVerse 6
- Kling O3
- Kling 2.6
- Kling O1 (Omni)
- Wan 2.6
- MiniMax Hailuo 2.3
- Kling 2.5
- Soul Standard
- Qwen Image 3
- Z-Image Turbo
Model catalog
THE MODELS YOU NEED, ALL IN ONE PLACE.
Kling 3.0 Standard generates videos from text prompts with options for sound, duration, aspect ratio, and multiple shots. It supports multi-prompt sequences and configurable detail via CFG scale for flexible video creation.
MiniMax H3 / Hailuo-03 preview integration using Video Generation V2.
Generate videos from text prompts with Wan 3.0 Prime.

Generate or edit campaign images with optional preset-guided Marketing Studio prompt enhancement.
Seedance 2.0 generates videos from text prompts, allowing customization of duration, resolution, aspect ratio, and optional audio. This model supports video creation up to 15 seconds with multiple aspect ratios and resolutions including 4K.
Seedance 2.5 generates videos from text prompts, allowing customization of duration, resolution, aspect ratio, output format, and optional audio generation. This model supports creating videos up to 30 seconds with flexible visual and audio settings.
Kling 3.0 Standard generates videos from text prompts with options for sound, duration, aspect ratio, and multiple shots. It supports multi-prompt sequences and configurable detail via CFG scale for flexible video creation.
MiniMax H3 / Hailuo-03 preview integration using Video Generation V2.
Generate videos from text prompts with Wan 3.0 Prime.

Generate or edit campaign images with optional preset-guided Marketing Studio prompt enhancement.
Seedance 2.0 generates videos from text prompts, allowing customization of duration, resolution, aspect ratio, and optional audio. This model supports video creation up to 15 seconds with multiple aspect ratios and resolutions including 4K.

Transform and refine source images with Grok Imagine 2.0.

Soul V2 Standard generates images from text prompts with customizable style, resolution, aspect ratio, and batch size. Users can enhance prompts and set a seed for reproducibility, making it suitable for varied creative visual outputs.
Generate videos from text prompts with Wan 3.0.
LTX-2.5 Fast Text to Video on Runware with native audio and optional camera movement.
LTX-2.5 Pro Text to Video on Runware with native audio and optional camera movement.
Multi-mode video generation with text-to-video, image-to-video, and reference-to-video.
Wan 2.7 - Text to Video. Configured Alibaba route; cloned from wan-27/text-to-video.
HappyHorse 1.1 - Text to Video. Configured Alibaba route; cloned from hh/text-to-video.

Ideogram 4.0 generates images from text prompts and allows image editing with adjustable aspect ratios and image influence. Users can control rendering speed and the degree to which the input image affects the output.

Recraft V4.1 Text to Image generates images from textual prompts with customizable resolution, aspect ratio, and output format. Users can specify colors and background color to tailor the visual style of the generated image.
Happy Horse 1.0 - Text to Video. Configured Alibaba route; cloned from hh/text-to-video.
PixVerse V6 Text to Video on Runware with optional native synchronized audio.
Kling O3 First/Last Frame generates videos from a starting image and optional ending image, allowing single or multiple prompt inputs to control the video content. Users can specify duration, aspect ratio, and sound settings to customize the output video.
Kling 2.6 Pro generates short videos from text prompts with customizable duration, aspect ratio, and sound options. Users can adjust the CFG scale to control the adherence to the prompt for creative flexibility.
Kling Omni First/Last Frame generates videos by animating between a specified first and optionally last frame image, guided by a text prompt. Users can customize duration, aspect ratio, and choose between standard and pro modes for different animation styles.
Wan 2.6 - Text to Video. Configured Alibaba route; cloned from wan-26/text-to-video.
MiniMax Hailuo 2.3 Standard is an image-to-video model that delivers physics-aware 768p results and runs with 2.5× higher efficiency
Kling 2.5 Turbo Standard converts a single image into a short video clip using a text prompt to guide the transformation. Users can specify video duration, CFG scale for prompt adherence, and provide negative prompts to refine output.

Create original images from written prompts with Soul Standard.

Generate PNG images from Chinese or English prompts with Alibaba Qwen Image 3.

Fast text-to-image generation with strong Chinese and English text rendering.
7-DAY LAUNCH OFFER
PICK ANY 4 MODELS. SAVE UP TO 50%
- Seedance 2.515% off$0.1748 / sec$0.2057
- Kling 3.015% off$0.1071 / sec$0.126
- MiniMax H315% off$0.1105 / sec$0.13
- Wan 3.0 Prime$0.068 / sec
- Marketing Studio Image15% off$0.0138 / image$0.0162
- Seedance 2.015% off$0.1196 / sec$0.1407
- Grok Imagine 2.0$0.04 / image
- Soul 2$0.0032 / image
- Wan 3.0$0.05 / sec
- LTX 2.5 Fast$0.09 / sec
- LTX 2.5 Pro$0.12 / sec
- Grok Imagine Video 1.5$0.08 / sec
- Wan 2.7$0.10 / sec
- Happy Horse 1.115% off$0.119 / sec$0.14
- Ideogram 4.0$0.06 / image
- Recraft 4.1$0.035 / image
- Happy Horse 1.015% off$0.119 / sec$0.14
- PixVerse 6$0.115 / sec
- Kling O315% off$0.0952 / sec$0.112
- Kling 2.615% off$0.119 / sec$0.14
- Kling O1 (Omni)15% off$0.0952 / sec$0.112
- Wan 2.6$0.10 / sec
- MiniMax Hailuo 2.3$0.0467 / sec
- Kling 2.515% off$0.0357 / sec$0.042
- Soul Standard$0.0938 / image
- Qwen Image 3$0.04 / image
- Z-Image Turbo$0.015 / image
Ideas to build
Don't start from a blank page
Content factory
Write one line about your product and get a creator-style video with the script, presenter, and voice ready.
Content factory Content factory Content factory Content factory Content factory Content factory
Fashion photoshoots
A full photoshoot without the studio. Consistent AI models wear your products in your brand's style - shot, retouched, and e-commerce ready in minutes, not weeks

Cinematic pipeline
Your idea, now in motion. Turn a short creative brief into a polished cinematic sequence without a production crew, expensive equipment, or weeks of post-production.
Works with your existing stack
Teams already using fal or Replicate can switch by swapping a single key and keep the rest of their code in place.
1 week offer
Sign up and save up to 50%
Seedance 2.5 generates videos from text prompts, allowing customization of duration, resolution, aspect ratio, output format, and optional audio generation. This model supports creating videos up to 30 seconds with flexible visual and audio settings.
Kling 3.0 Standard generates videos from text prompts with options for sound, duration, aspect ratio, and multiple shots. It supports multi-prompt sequences and configurable detail via CFG scale for flexible video creation.
MiniMax H3 / Hailuo-03 preview integration using Video Generation V2.
Generate videos from text prompts with Wan 3.0 Prime.

Generate or edit campaign images with optional preset-guided Marketing Studio prompt enhancement.
Seedance 2.0 generates videos from text prompts, allowing customization of duration, resolution, aspect ratio, and optional audio. This model supports video creation up to 15 seconds with multiple aspect ratios and resolutions including 4K.

Transform and refine source images with Grok Imagine 2.0.

Soul V2 Standard generates images from text prompts with customizable style, resolution, aspect ratio, and batch size. Users can enhance prompts and set a seed for reproducibility, making it suitable for varied creative visual outputs.
Analytics
See where every dollar goes
Track spend by day, model, and workflow, with discounts shown on your invoice. Pick a period, export the CSV, and send it to finance.
Get started
Three steps from key to content
The same flow for every image, video, and audio model. JavaScript, Python, and cURL examples are all in the docs.
- 1
Configure credentials
export HF_API_KEY_ID="your-api-key-id"export HF_API_KEY_SECRET="your-api-key-secret" - 2
Submit a generation
curl --request POST \ --url https://api.higgsfield.ai/bytedance/seedance-2.0/text-to-video \ --header "Authorization: Key ${HF_API_KEY_ID}:${HF_API_KEY_SECRET}" \ --header "Content-Type: application/json" \ --data '{ "prompt": "A cinematic tracking shot along a sunlit coastal road", "resolution": "720p", "generate_audio": true, "duration": 5, "aspect_ratio": "16:9" }' - 3
Check the result
curl --silent --show-error --fail-with-body \ --url "https://api.higgsfield.ai/requests/${REQUEST_ID}/status" \ --header "Authorization: Key ${HF_API_KEY_ID}:${HF_API_KEY_SECRET}" | jq
Community over 25 MILLION USERS
Join a global creative network where people generate AI images, share ideas, and inspire each other every day.




Trusted by 5.000+ people worldwide
Still have questions?
We’ve answered the most frequently asked questions

