kling/kling-v2-t2i

文档
Schema

[Core Function] Kling V2 T2I is an older generation text-to-image model. [Strengths] Offered improved multi-subject tracking and better texture details over V1. Maintained for backward compatibility. [Best For] Existing legacy integrations and workflows that strictly depend on this specific model version's quirks. [Limitations] Do NOT use this for new creations. It is a legacy model maintained for backward compatibility. [Routing] Only use if explicitly requested; otherwise use Kling V3 T2I.

$0.0200/img
text-to-image

输入

Image description text, supports Chinese and English
Negative prompt describing undesired elements
Image aspect ratio
16:9
Number of images to generate per request
Image resolution. V2 supports both 1K and 2K
1k

结果

暂无结果

运行模型后，结果将在这里显示。

Next:

README

"## What Kling V2 T2I Does
Kling V2 T2I is an older-generation text-to-image model maintained for legacy integrations. It generates images from text prompts and supports resolution up to 2K, but is intended for existing workflows rather than new projects.

Key Features

  • Text-to-Image Generation: Creates images from bilingual (Chinese/English) prompts up to 2,500 characters.
  • Negative Prompts: Accepts a negative_prompt (up to 2,500 chars) to exclude unwanted elements.
  • Up to 2K Resolution: Supports 1k or 2k output.
  • Wide Aspect-Ratio Support: Offers 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, and 21:9.
  • Batch Output: Generate 1–9 images per request via n.
  • Asynchronous Architecture: Uses a ““Create Task → Poll Result”” API workflow for reliable integration.

How to Use Kling V2 T2I

  1. Write a prompt (Chinese or English, up to 2,500 characters) describing the image, plus an optional negative_prompt.
  2. Submit a POST request to the /kling/kling-v2-t2i endpoint with your prompt and optional negative_prompt, aspect_ratio, resolution, and n.
  3. Receive an AsyncTaskResponse with a task_id and polling URL.
  4. Poll GET https://api.modellix.ai/api/v1/tasks/{task_id} to monitor the task.
  5. Once complete, retrieve and download the generated image(s).

Best Use Cases

  • Legacy Integrations: Keep existing pipelines that depend on Kling V2 running.
  • Backward-Compatibility Testing: Reproduce or validate older outputs.
  • Maintenance Workflows: Support apps not yet migrated to the latest Kling version.

Tips for Better Results

  • Prefer a Newer Model for New Work: This is a legacy model — use Kling V3 T2I for new creations unless V2 is explicitly required.
  • Use 2K for More Detail: Set resolution: 2k when you need sharper output (an advantage over V1/V1.5).
  • Use Negative Prompts: Add a negative_prompt to filter out unwanted elements.
  • Generate in Batches: Increase n (up to 9) to compare multiple options per request.
  • Write Clear, Specific Prompts: Both Chinese and English are supported — be precise about subject, style, and composition."

参数

参数名 描述 类型 必填 枚举值
prompt Image description text, supports Chinese and English string 是 -
negative_prompt Negative prompt describing undesired elements string 否 -
aspect_ratio Image aspect ratio string 否 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9
n Number of images to generate per request integer 否 -
resolution Image resolution. V2 supports both 1K and 2K string 否 1k, 2k

价格

单位: $/img

价格
$0.0200/img