Kling 3.0

kwaivgi/kling-v3.0/text-to-video

kwaivgi/kling-v3.0/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

Powiązane modele

Pełne parametry, schemat wyjścia i aktualne ceny

Rynek API modeli AIJedna platforma do wszystkiegoNajpopularniejszyRegulaminPrzeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.
promptPrompttextarea—≤ 5000 chars
negative_promptNegative Prompttextarea—≤ 5000 chars
durationDurationselect53 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | …
resolutionGeneration Modeselect720P720P | 1080P | 4K
aspect_ratioAspect Ratioselect16:916:9 | 9:16 | 1:1
cfg_scaleCfg Scaleslider0.50 ~ 1 · step 0.01
soundSoundbooleanfalse—
element_listElement Listarray<object>—0–3 items
↳element_idElement Idtext——
multi_shotMulti Shotboolean——
shot_typeShot Typeselect—customize | intelligence
multi_promptMulti Promptarray<object>——
↳durationDurationnumber5—
↳promptPrompttext——

Pełne parametry, schemat wyjścia i aktualne ceny

Dowiedz się więcejJedna platforma do wszystkiegoPrzeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.
videosarray<string>

API

Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/kwaivgi/kling-v3.0/text-to-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "prompt": "A futuristic cityscape at sunset with flying cars and glowing skyscrapers.",
    "negative_prompt": "Crowded streets, dull colors, and broken buildings.",
    "duration": 10,
    "resolution": "720P",
    "aspect_ratio": "16:9",
    "cfg_scale": 0.7,
    "sound": true,
    "shot_type": "intelligence"
  }
}'

# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
  -H "Authorization: Bearer YOUR_API_KEY"
Python
import time, requests

API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}

# 1) Submit
resp = requests.post(
    "https://www.namifusion.com/api/v1/marketplace/run/kwaivgi/kling-v3.0/text-to-video",
    headers=HEADERS,
    json={
        "input": {
            "prompt": "A futuristic cityscape at sunset with flying cars and glowing skyscrapers.",
            "negative_prompt": "Crowded streets, dull colors, and broken buildings.",
            "duration": 10,
            "resolution": "720P",
            "aspect_ratio": "16:9",
            "cfg_scale": 0.7,
            "sound": True,
            "shot_type": "intelligence"
        }
    },
)
resp.raise_for_status()  # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()

# 2) Poll until a terminal state (completed / failed / cancelled).
#    This model is allowed up to 300s server-side.
deadline = time.time() + 360
while task.get("status") not in ("completed", "failed", "cancelled"):
    if time.time() > deadline:
        raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
    time.sleep(3)
    poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
    poll.raise_for_status()
    task = poll.json()

print(task["status"], task.get("output"))
JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };

// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/kwaivgi/kling-v3.0/text-to-video", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "prompt": "A futuristic cityscape at sunset with flying cars and glowing skyscrapers.",
      "negative_prompt": "Crowded streets, dull colors, and broken buildings.",
      "duration": 10,
      "resolution": "720P",
      "aspect_ratio": "16:9",
      "cfg_scale": 0.7,
      "sound": true,
      "shot_type": "intelligence"
    }
  }),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();

// 2) Poll until a terminal state (completed / failed / cancelled).
//    This model is allowed up to 300s server-side.
const deadline = Date.now() + 360 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
  if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
  await new Promise((r) => setTimeout(r, 3000));
  const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
  if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
  task = await poll.json();
}

console.log(task.status, task.output);

Dokumentacja API

Kling 3.0 Standard

High-quality text-to-video generation with cinematic visuals and synchronized audio

Kling 3.0 Standard is a cost-efficient text-to-video model designed for smooth motion, cinematic visuals, and accurate prompt adherence. With flexible duration options, multiple aspect ratios, and optional synchronized sound, it delivers ready-to-share clips at affordable pricing. The model ensures high performance with no cold starts and is accessible via a REST inference API.


🚀 Key Features

  • Cinematic Visuals: Generate videos with smooth motion and high-quality visuals directly from text prompts.
  • Flexible Duration: Create clips ranging from 3 to 15 seconds to suit various production needs.
  • Multiple Aspect Ratios: Supports 16:9 (landscape), 9:16 (portrait), and 1:1 (square) formats for diverse platforms.
  • Synchronized Audio: Optionally generate synchronized sound alongside the video for immersive experiences.
  • Precise Prompt Control: Utilize negative prompts and CFG scale for fine-tuned output.
  • Multi-Prompt Support: Chain multiple prompts for scene transitions and consistent storytelling.

🛠️ Technical Specifications

ParameterTypeDefault ValueRange/OptionsDescription
PromptString--Text description of the scene, motion, camera style, and atmosphere.
Negative PromptString--Elements to exclude from the video.
DurationInteger53–15 secondsLength of the generated video.
Aspect RatioString16:916:9, 9:16, 1:1Output format for the video.
CFG ScaleNumber0.50.0–1.0Prompt adherence strength; higher values increase relevance to the prompt.
SoundBooleanDisabledEnabled/DisabledGenerate synchronized sound alongside the video.
Shot TypeStringCustomizeCustomize, IntelligentEditing mode; customize for manual control, intelligent for auto-detection.
Multi-PromptArray--Additional prompt segments for scene transitions and progressions.
Element ListArray--Reference list of visual elements for consistency.

💰 Pricing

ResolutionAttributePrice per Second (USD)
720PMuted0.0840
720PWith Audio0.1260
1080PMuted0.1120
1080PWith Audio0.1680
4KMuted0.4200
4KWith Audio0.4200

💡 Best Use Cases

  • Social Media Content: Generate portrait or square clips for TikTok, Reels, and Shorts at scale.
  • Concept Visualization: Quickly bring creative ideas and moods to life from text descriptions.
  • Marketing & Advertising: Produce promotional video content without a film crew.
  • Prototyping: Test visual ideas and prompt variations at Standard pricing before committing to Pro.

🔗 Related Models

  • Kling V3.0 Pro Text-to-Video: Maximum quality with Pro-tier capabilities.
  • Kling V3.0 Std Image-to-Video: Animate still images at Standard pricing.
  • Kling Video O3 Std Text-to-Video: Next-generation O3 Standard text-to-video.

Pro Tips

  • The more specific your prompt, the better — include camera angle, lighting style, character behavior, and atmosphere.
  • Use negative prompts to avoid common artifacts like blurry faces or unwanted motion.
  • Match aspect ratio to your platform: 16:9 for YouTube, 9:16 for TikTok, 1:1 for Instagram.
  • Enable sound for scenes with ambient environments, crowds, or action for a more immersive result.
  • Use shorter durations (3–5s) for rapid iteration, longer (10–15s) for final output.

Notes

  • Only the prompt is a required field; all other parameters are optional.
  • Duration range: minimum 3 seconds, maximum 15 seconds.
  • Sound generation increases cost by 1.5×.
  • Use the Kling Elements tool to generate visual elements and reference their IDs in your prompts.

Powiązane modele

xAI Grok Imagine Video v1.5 Text to Video
Tekst na wideoX Ai

xAI Grok Imagine Video v1.5 Text to Video

x-ai/grok-imagine-video-v1.5/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

od $0.840 / za uruchomienie
MiniMax H3 Text to Video
Tekst na wideoMinimax

MiniMax H3 Text to Video

minimax/h3/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

od $0.650 / za uruchomienie
ltx-2.5/text-to-video
Tekst na wideoLtx 2.5

ltx-2.5/text-to-video

ltx-2.5/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

od $0.500 / za uruchomienie
Kling Omni Video O3 Standard Text-To-Video
Tekst na wideoKling

Kling Omni Video O3 Standard Text-To-Video

kwaivgi/kling-video-o3/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

od $0.420 / za uruchomienie
Kling V2.6 Text to Video API
Tekst na wideoKling

Kling V2.6 Text to Video API

kwaivgi/kling-v2.6/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

od $0.210 / za uruchomienie
Gemini Omni Flash Text to Video API
Tekst na wideoGoogle

Gemini Omni Flash Text to Video API

google/gemini-omni-flash/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

od $1.04 / za uruchomienie
Seedance 2.0 Mini Text to Video
Tekst na wideoDoubao

Seedance 2.0 Mini Text to Video

doubao/seedance-2.0-mini/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

od $0.378 / za uruchomienie
Seedance 2.5 Text-to-Video
Tekst na wideoDoubao

Seedance 2.5 Text-to-Video

doubao/seedance-2-5/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

od $1.155 / za uruchomienie