Blog
AI Image & Video API Guides
Hands-on model tests, production tutorials, prompt techniques, and current API pricing for generative media teams.
Hailuo 2.3 API Guide: Text-to-Video, Image-to-Video and Fast
Three endpoints: text-to-video, image-to-video and Fast image-to-video. Billed per clip: $0.40 for 6 s and $0.80 for 10 s; Fast is $0.27 and $0.46. The input is prompt, duration as a string, prompt_optimizer, and one image_url for image-to-video.
How to Use the hailuo 2.3 Fast Image to Video API: curl, Python, and a Working Request
Integrate hailuo-2.3-fast/image-to-video through hiapi's async task API: POST /v1/tasks with prompt, a single image_url, and a string duration, then poll or register a callback and download the MP4 before the temp URL expires. Every schema rule here was checked against the live validator: image_url is singular, duration must be the string '6' or '10', and resolution/aspect_ratio/seed are rejected as unknown fields.
Seedream 5.0 Pro Text-to-Image Prompts: 6 Copy-Paste Recipes With Real Outputs
Six copy-paste prompt recipes for seedream-5.0-pro/text-to-image, each shown with the real, first-take output it produced. 13 of 13 quoted text strings rendered correctly across the set — movie-poster type hierarchy, curved label text, a magazine masthead and vertical katakana. Includes the task-API call, the 1K ($0.075) vs 2K ($0.15) price lever, and a five-rule cheatsheet for writing your own prompts.
How to use seedream-5.0-pro/text-to-image via the hiapi API: curl, Python, and a working request
seedream-5.0-pro/text-to-image runs on hiapi's async /v1/tasks endpoint: POST to create, poll data.status or use a callback, then download data.output[0].url before it expires. The input schema is strict and minimal: exactly three required fields — prompt, aspect_ratio (8-value enum), resolution (1K or 2K) — and anything extra (n, seed, size) is rejected with a 400. Copy-paste curl and stdlib-only Python examples included, plus text-rendering prompt tips and the exact 400/401 error messages with fixes.
How to use seedream-5.0-pro/image-to-image via the hiapi API: curl, Python, and a working request
seedream-5.0-pro/image-to-image runs on hiapi's unified async /v1/tasks endpoint: create a task, poll data.status (or use a callback), download data.output[0].url before it expires. All four input fields are required and the schema is strict: prompt, image_urls (array of 1-10 public URLs), aspect_ratio (9-value enum incl. match_input_image), resolution (1K or 2K only). Copy-paste curl and stdlib-only Python examples included, plus the exact 400/401 error messages the API returns and how to fix each.
Build an AI Image Prompt Enhancer: LLM Prompt Expansion for ideogram-v4 and flux-2
Prompt expansion -- a cheap LLM pass that enriches short prompts before the image API -- is now a standard step in image pipelines, and this recipe builds it in ~80 lines of Python. ideogram-v4 and flux-2/text-to-image have no built-in expander (unlike qwen-image-2.0's prompt_extend or flux-1.1-pro's prompt_upsampling), so you bring your own -- with one expander system prompt per model family. Both models run through hiapi's unified async task API: POST /v1/tasks, poll or callback, download output[0].url before it expires; schemas differ per model and are validated strictly.
Seedance 2.0 One-Shot Video: Anatomy of a 4K POV Flythrough Prompt
The clip in this post is one continuous 15-second POV shot from a single Seedance 2.0 prompt — no cuts, no keyframes, and the audio was generated with it. The prompt does six jobs: lock the camera, ban its carrier, stack the corridor with near-misses, script the ending, fix the grade, and score the sound. Seedance 2.0 renders native 4K (3840×2160); iterate at 720p ($0.293/s) and re-run the keeper at 4k ($1.486/s, July 2026 pricing). Full prompt and a copy-paste /v1/tasks request included.
Wan 2.7 Image-to-Video Prompt Recipes: 3 Copy-Paste Prompts With Real Outputs
Three copy-paste image-to-video prompt recipes for wan2.7-video/image-to-video, each shown with the input frame it started from and the real, first-take clip it produced. Covers the three core i2v jobs — product motion with a locked camera, portrait micro-performance, and explicit camera movement — plus the task API request shape and schema quirks. All 14 seconds of finished 720P video in this post cost $1.40 at the standard $0.10/second tier, with every price checked against the live pricing API.
Seedream 5.0 Lite Prompt Recipes: 6 Copy-Paste Prompts With Real Outputs
Six copy-paste prompt recipes for seedream-5.0-lite/text-to-image, each shown with the real, first-take output it produced. Covers the model's three edges: multilingual text rendering (16/16 strings correct), web-knowledge entity grounding, and strict instruction following. Includes the task-API call, the 2K/4K resolution gotcha, and a five-rule pattern cheatsheet for writing your own prompts.
How to Use the MiniMax Music API (minimax-music-1.5): curl, Python, and a Working Request
minimax-music-1.5 generates full songs from a style prompt plus lyrics via hiapi's async /v1/tasks endpoint. The verified input schema takes exactly four fields: prompt (10-300 chars), lyrics (10-600 chars), and optional sample_rate and bitrate enums. Copy-paste curl and Python examples cover create, poll, download, plus production callbacks with when:'final'.
Build with the models you just read about.
Compare image, video, and audio models, then use the same API workflow in production.