Hy Image 3.5 Preview Spicy

Hy Image 3.5 Preview Spicy is an advanced uncensored image generation and editing model built on Tencent Hunyuan's flagship Hy Image 3.5 Preview architecture. Designed as a Spicy uncensored model, it completely bypasses standard content filters to unlock unconstrained creative freedom across cinematic portraiture, complex concept art, and high-fidelity visual storytelling. Featuring reasoning-first spatial composition, support for multi-image reference conditioning, precise multilingual typography rendering, and seamless multi-turn conversational editing, Hy Image 3.5 Preview Spicy empowers professional creators, designers, and agencies to produce studio-grade visual assets without creative boundaries.

Hy-Image-3.5-preview Spicy

Tencent's Hy-Image-3.5-preview Spicy text-to-image and multimodal image-editing model generates high-quality images from natural-language instructions and reference images. It provides a ready-to-use REST inference API with excellent visual quality, fast inference, and chat-based multimodal parameter formatting.

Base URL

https://api.icreat.ai

Authentication

All API requests must be authenticated with an API Key. You can obtain an API Key from the console.

export ICREAT_API_KEY="your-api-key-here"

HTTP Request Headers

import os

API_KEY = os.environ.get("ICREAT_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer " + API_KEY,
}

Protect your API Key Never expose your API Key in client-side code or public repositories. Use environment variables or a backend proxy.

Code Examples

Image generation uses a two-step async flow: submit a task to receive a task_id, then poll via query task result; the response includes status and result ([] while processing; on SUCCEEDED, result holds resources and costUSD is present). The examples below demonstrate how to format requests using multimodal message structures.

1. Submit Task

Send a generation request to the submit endpoint using the messages array structure.

POST/v1/task/submit/tencent/hy-image-3.5-preview-global

curl --fail-with-body --connect-timeout 10 --max-time 60 \
  -X POST "https://api.icreat.ai/v1/task/submit/tencent/hy-image-3.5-preview-global" \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
  "size": "1080x1080",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "示例多行\n文本"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://example.com/example.png"
          }
        }
      ]
    }
  ]
}'

2. Query Task Result (Poll)

Use the task_id from submit to poll progress until completed.

POST/v1/task/result

curl --fail-with-body --connect-timeout 10 --max-time 60 \
  -X POST "https://api.icreat.ai/v1/task/result" \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{"task_id": "task-xxx"}'

Input Schema

Submit Task — Input

The following parameters are accepted in the submit request body.

Total: 2 Required: 2 Optional: 0

sizestringrequired

Dimensions of the target output image. Supports resolutions such as 1080x1080, 1024x1024, 1280x720, 2048x2048, and custom aspect ratios.

messagesarray[object]required

A structured conversation list providing generation instructions and optional reference images.

Query Task Result — Input

Total: 1 Required: 1 Optional: 0

task_idstringrequired

The task ID returned from the submit endpoint.

Output Schema

Submit Task — Output

Total: 1

task_idstring

Unique identifier for the async task. Use this ID to poll status and retrieve results.

Query Task Result — Output

Total: variable

statusstring

Current task status. result is usually [] until success; on SUCCEEDED, result holds resources and costUSD is present.

SUBMITTEDSUCCEEDEDFAILED

resultarray[object]

Generated resources. Empty array while processing or on failure; array of objects on success.

costUSDnumber

Task cost in USD. Present only when status is SUCCEEDED.

LLM Prompt

The Markdown below is an LLM-friendly prompt you can paste into AI assistants (e.g. Cursor, ChatGPT) to help them understand this model's API, call flow, and key parameters. Use Copy for AI or copy from the code block below.

# tencent/hy-image-3.5-preview-global

> Tencent's Hy-Image-3.5-preview Spicy text-to-image and multimodal image model generates high-quality images from conversational text prompts and reference image blocks.

## Overview

Use the iCreat two-step async task API: submit a generation request, then poll the query task result endpoint; on success read resources from `result` (includes `costUSD`).

## API Info

- **Base URL**：`https://api.icreat.ai`
- **Submit endpoint (POST)**：`/v1/task/submit/tencent/hy-image-3.5-preview-global`
- **Query result endpoint (POST)**：`/v1/task/result`
- **Model ID**：`tencent/hy-image-3.5-preview-global`
- **Auth**：`Authorization: Bearer ${ICREAT_API_KEY}`

## Call Flow

1. **Submit**: POST submit path with body per Input Notes; response `{ "task_id": "..." }`
2. **Query result**: POST `/v1/task/result` with `{ "task_id": "..." }`; response includes `status` and `result` (`[]` while processing); on `SUCCEEDED`, `result` holds resources and `costUSD` is present; read `url` or `download_url` when `type` is `Image`

### Input Notes

- Request body uses top-level fields: `size` and `messages`
- Required: `size`, `messages`
- `size` (required): Dimensions of the generated image (e.g., `1080x1080`, `1024x1024`, `1280x720`, `2048x2048`).
- `messages` (required): Array of user role objects with multimodal `content` blocks:
  - Text item: `{ "type": "text", "text": "..." }`
  - Image item: `{ "type": "image_url", "image_url": { "url": "..." } }`

### Output Notes

- Poll: read `status`; `result` is `[]` while processing
- Success: `result` is `[{ "type": "Image", "url": "...", "download_url": "..." }]` plus `costUSD`

## Notes

- Use the same `task_id` across both steps; `result` is `[]` while processing — keep polling
- `FAILED` is terminal — check request parameters or reference media