Cogview 4 | High-Quality Text-to-Image API

Z.AI CogView-4 Text-to-Image

CogView-4 is Z.AI's high-quality text-to-image generation model designed to transform natural-language descriptions into precise, personalized visuals. It excels at interpreting user intent — producing images that accurately reflect your creative vision with strong compositional clarity and visual appeal.

Why Choose This?

Precise prompt understanding Accurately interprets detailed prompts to generate images that match your description — balancing subject, context, and style with strong fidelity.
Flexible quality modes Choose standard for fast results (5-10 seconds) or hd for richer detail and visual depth (~20 seconds).
Wide aspect ratio support Multiple presets from square to portrait, landscape, and ultra-wide formats for social, web, or print use.
Prompt Enhancer Built-in tool to automatically improve your prompts for better generation results.
Fast, reliable generation Optimized for quick turnaround with stable output quality — ideal for rapid ideation and creative iteration.

Parameters

Parameter	Required	Description
prompt	Yes	Text description of the image you want to generate
size	No	Output dimensions (default: 1024*1024)
quality	No	Rendering quality: standard or hd

Size Options

Size	Orientation	Best For
1024*1024	Square	Social posts, avatars, album art
768*1344	Portrait	Mobile screens, stories, vertical banners
864*1152	Portrait	Mobile displays, vertical content
1344*768	Landscape	Web headers, presentations
1152*864	Landscape	Widescreen designs, banners
1440*720	Ultra-wide	Cinematic layouts, panoramic visuals
720*1440	Ultra-tall	Immersive vertical content

Quality Options

standard — Faster generation (5-10 seconds), good for previews and rapid iteration
hd — Higher detail and visual richness (~20 seconds), recommended for final outputs

How to Use

Write your prompt — describe the subject, setting, mood, and visual style.
Select size — choose dimensions that match your intended use.
Choose quality — standard for speed, hd for maximum detail.
Run — click Run, preview the result, and iterate if needed.

Pricing

Item	Cost
Per image	$0.01

Simple flat-rate pricing regardless of size or quality settings.

Best Use Cases

Social Media Graphics — Create on-brand visuals for posts, stories, and ads.
Concept Art — Generate ideas for storyboarding and creative exploration.
Product Mockups — Produce e-commerce imagery and marketing materials.
Presentations — Visualize concepts for slides and educational content.
Web Design — Create headers, banners, and promotional visuals.

Pro Tips

Be specific about composition, lighting, and style to guide the model toward your vision.
Use hd quality for final outputs and standard for quick iterations.
Generated images are valid for 7 days — download outputs you want to keep.

Notes

Please ensure your prompts comply with content guidelines. If an error occurs, review your prompt and try again.

Related Models

Google Nano Banana Pro — Google's fast text-to-image model with 4K output support.
FLUX.2 Pro — Flagship-quality generation with cinematic detail and strong prompt fidelity.
Seedream 4.5 — text-to-image model focused on visual aesthetics and style accuracy.
Qwen Image 2512 — model with exceptional text rendering capabilities.

Cogview 4 API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/z-ai/cogview-4 with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Cogview 4 below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/z-ai/cogview-4" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "size": "1024*1024",
    "quality": "hd",
    "enable_sync_mode": false,
    "enable_base64_output": false
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("z-ai/cogview-4", {
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "size": "1024*1024",
        "quality": "hd",
        "enable_sync_mode": false,
        "enable_base64_output": false
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "z-ai/cogview-4",
    {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "size": "1024*1024",
    "quality": "hd",
    "enable_sync_mode": false,
    "enable_base64_output": false
}
)

print(output["outputs"][0])  # → URL of the generated output

Cogview 4 API — Frequently asked questions

What is the Cogview 4 API?

Cogview 4 is a Z Ai model for image generation, exposed as a REST API on WaveSpeedAI. Z-AI CogView-4 generates high-quality images from text prompts with a quick and accurate understanding of user descriptions, letting AI express images more precisely and personally. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Cogview 4 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 prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/z-ai/z-ai-cogview-4.

How much does Cogview 4 cost per run?

Cogview 4 starts at $0.010 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 Cogview 4 accept?

Key inputs: `prompt`, `size`, `enable_base64_output`, `enable_sync_mode`, `quality`. 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/z-ai/z-ai-cogview-4.

How long does Cogview 4 take to generate?

Average end-to-end generation time on WaveSpeedAI is around 36 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Cogview 4 outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Z Ai). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

示例查看全部

相关模型

README