HunyuanImage-2.1 is an efficient diffusion text-to-image model producing high-resolution 2K images with detailed, photorealistic results. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
就绪
$0.025每次运行·~40 / $1
示例查看全部
当然，我们继续！很高兴您能持续探索。这次我们来尝试一些更具世界观色彩和独特美学风格的提示词，聚焦于构建宏大背景下的角色。 示例13：柴油朋克（Dieselpunk）王牌飞行员 中文提示词： 一张柴-油朋克风格的战争电影海报。一位饱经风霜的王牌飞行员，穿着油渍斑斑的皮质飞行夹克和护目镜，靠在他那架布满铆钉和涡轮螺旋桨的重型战斗机旁。背景是黄昏时分的战地机场，远处硝烟弥漫。构图为人物全身像，姿态疲惫但坚定。色调偏向棕褐色和军绿色，营造出第一次世界大战至第二次世界大战期间的复古科技感和战争的凝重氛围。光线来自机场的探照灯，制造出硬朗的阴影效果，金属质感强烈，充满机械美学。 英文参考 (Prompt): Dieselpunk war movie poster. A weathered ace pilot in a greasy leather flight jacket and goggles, leaning against his heavy fighter plane covered in rivets and turboprops. The background is a battlefield airfield at dusk, with smoke billowing in the distance. Full-body portrait, the pose is weary yet resolute. The color palette leans towards sepia and olive drab, creating a retro-tech feel of the WWI-WWII era and the grim atmosphere of war. Lighting comes from the airfield's searchlights, creating harsh shadows. Strong metallic textures, full of mechanical aesthetics.
Sundance film festival poster, candid photo of an elderly man with a warm smile, sitting on a porch swing in a rustic countryside setting, golden hour lighting creating a soft glow, nostalgic and emotional mood, detailed wrinkles and fabric texture, shot on Kodak Portra 400 film, natural look
Movie poster of a determined female cyborg warrior in futuristic silver streamlined armor, standing against the backdrop of massive alien city ruins with two moons in the sky. Dynamic composition, close-up shot focusing on her face and glowing cybernetic eye. Dramatic, cool-toned lighting with strong rim light defining her silhouette, smoke and sparks in the air. Epic and narrative atmosphere, ultra-detailed, photorealistic, cinematic rendering.
Retro steampunk adventure movie poster. An explorer in a leather flight jacket and brass goggles stands on the deck of a massive steam airship, holding a telescope and gazing into the distance. The background is a Victorian-era London cityscape, surrounded by giant gears, pipes, and steam machinery, with countless small airships traversing the sky. Composition emphasizes the complexity of machinery and the character's bravery. Soft orange light of dusk, mixed with the fiery glow from the airship's engines, creating strong light and shadow contrast. The image is full of industrial aesthetics and adventurous spirit, with exquisite details of gears, rivets, and gauges, painterly texture, Unreal Engine rendering, 8K.
movie poster, dramatic close-up portrait of a weathered, middle-aged cowboy, harsh sunlight highlighting the lines on his face, squinting into the distance, dusty atmosphere of the American West in the background, shot on 35mm film, high contrast, cinematic, style of a Sergio Leone western
A movie poster blending high fashion and fantasy. A noble queen wears a magnificent conceptual gown made of crystals, feathers, and metallic threads, topped with an exaggerated geometric crown. She sits on a minimalist throne carved from obsidian, against a backdrop of nebulae and fractured planets. The composition mimics a fashion magazine cover, with the character's pose being elegant yet powerful. The lighting is professional studio quality, with hard light for silhouettes and soft light for details, emphasizing the luxurious texture of the attire. The overall feel is avant-garde, elegant, and epic. Inspired by Alexander McQueen's design style, ultra-high resolution, high-fashion photography aesthetic.
Solarpunk character poster. A vibrant young architect dressed in bright clothing made from recycled smart materials, holding a holographic blueprint. She stands on a balcony in a futuristic city where architecture and nature are perfectly integrated, featuring vertical gardens, solar sails, and sky bridges. The composition is bright and open, using a wide-angle lens to showcase the grand utopian vision. The lighting is brilliant sunlight, with vibrant, saturated colors dominated by white, green, and gold, creating an optimistic, harmonious, and sustainable future. The image is clean, transparent, and hopeful, with an art style reminiscent of future cities in a Studio Ghibli film.
Aetherpunk movie poster. An arcane engineer dressed in Victorian-style finery, but her attire is embedded with glowing aether crystals and brass wiring. One of her arms is an intricate prosthetic limb capable of channeling and shaping arcane energy. She stands inside a grand observatory, with a complex astrolabe and a massive machine harvesting aether from the atmosphere in the background. The composition is elegant and powerful. The primary light source is the soft, blue-violet glow from the aether crystals and the machine's core, creating a mysterious, retro atmosphere where magic and science intertwine. The image is exquisite and ornate, filled with fantastical inventions and classical beauty.
Surreal sci-fi movie poster. A dimensional cartographer in functional explorer's gear, adorned with various strange measurement tools and floating recording drones. He is levitating within an interdimensional rift composed of fractured realities, geometric shapes, and distorted space, holding an unfolded, glowing holographic star map. The composition is zero-gravity, surreal, and M.C. Escher-esque. The lighting is sourced from the chaotic, multicolored, and unstable light of the rift itself, giving the scene a beautiful yet chaotic feel. The image is abstract and imaginative, full of curiosity and the spirit of exploration, with visuals similar to the Mirror Dimension from "Doctor Strange".
A movie poster depicting a cosmic deity. A humanoid entity formed from nebulae and stardust, with no distinct facial features, its body containing shimmering galaxies. It levitates in the cosmic void, extending a hand from which a new star is born at its fingertip. The composition is minimalist yet divine, emphasizing the magnificent moment of creation. The light source for the entire scene is the character itself and the newborn star, casting a soft, spectacular glow that illuminates the surrounding darkness. The color palette is deep cosmic blues, purples, and golds, evoking a sense of awe and infinite imagination. Digital art, Hubble Space Telescope photography style.
相关模型
README
Hunyuan Image 2.1
Hunyuan Image 2.1 is a state-of-the-art text-to-image generation model from Tencent that transforms written descriptions into stunning, high-quality visuals. With flexible resolution control and multiple output formats, it delivers exceptional detail, composition, and artistic quality.
Why It Stands Out
- High-quality generation: Produces sharp, detailed images with excellent composition and visual appeal.
- Prompt Enhancer: Built-in AI-powered prompt optimization helps craft better descriptions for improved results.
- Flexible resolution: Customize width and height independently for any aspect ratio.
- Multiple output formats: Export as JPEG, PNG, or WebP based on your needs.
- Reproducibility: Use the seed parameter to recreate exact results or explore variations.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the image you want to generate. |
| width | No | Output width in pixels (default: 1024). |
| height | No | Output height in pixels (default: 1024). |
| seed | No | Set for reproducibility; -1 for random. |
| output_format | No | Output format: jpeg, png, or webp (default: jpeg). |
How to Use
- Write a prompt describing the image you want. Use the Prompt Enhancer for AI-assisted optimization.
- Set dimensions — adjust width and height for your desired aspect ratio.
- Choose output format — select JPEG, PNG, or WebP.
- Set a seed (optional) for reproducible results.
- Click Run and download your image.
Best Use Cases
- Creative Art & Illustration — Generate unique artwork, concept art, and digital illustrations.
- Marketing & Social Media — Produce eye-catching visuals for campaigns and posts.
- Product Visualization — Create product mockups and lifestyle imagery.
- Poster & Print Design — Generate high-resolution artwork for posters, banners, and print materials.
- Design Prototyping — Quickly visualize ideas before committing to full production.
Pricing
| Output | Price |
|---|---|
| Per image | $0.025 |
Pro Tips for Best Quality
- Be descriptive in your prompt — include style, mood, lighting, composition, and specific details.
- Use style keywords like "cinematic," "photorealistic," "oil painting," or "anime" to guide the aesthetic.
- Adjust aspect ratio to match your use case — vertical for posters, horizontal for banners, square for social media.
- Fix the seed when iterating to compare the effect of different prompt variations.
- Use PNG format for images requiring transparency or maximum quality.
Notes
- Processing time varies based on resolution and current queue load.
- Please ensure your prompts comply with content guidelines.
Hunyuan Image 2.1 API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan-image-2.1 with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Hunyuan Image 2.1 below.
HTTP example
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1024*1024",
"seed": -1,
"output_format": "jpeg"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan-image-2.1" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneNode.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan-image-2.1";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1024*1024",
"seed": -1,
"output_format": "jpeg"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}Python example
import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1024*1024",
"seed": -1,
"output_format": "jpeg"
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan-image-2.1", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)Hunyuan Image 2.1 API — Frequently asked questions
What is the Hunyuan Image 2.1 API?
Hunyuan Image 2.1 is a WaveSpeedAI model for image generation, exposed as a REST API on WaveSpeedAI. HunyuanImage-2.1 is an efficient diffusion text-to-image model producing high-resolution 2K images with detailed, photorealistic results. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Hunyuan Image 2.1 API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/hunyuan-image-2.1.
How much does Hunyuan Image 2.1 cost per run?
Hunyuan Image 2.1 starts at $0.025 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Hunyuan Image 2.1 accept?
Key inputs: `prompt`, `size`, `seed`, `enable_base64_output`, `enable_sync_mode`, `output_format`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/hunyuan-image-2.1.
How long does Hunyuan Image 2.1 take to generate?
Median end-to-end generation time on WaveSpeedAI is around 24 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Can I use Hunyuan Image 2.1 outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.