Image
CogView
Generate images from detailed descriptions with CogView 4.
- Text to image
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for CogView. Review your own result before publishing.
A starting point.
Specify subjects, their arrangement, lighting and materials for a scene with several visual requirements.
Before you publish.
Verify object count, spatial relationships and whether unwanted details remain.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Settings and model questionsCheck the available settings and guidance when preparing your input.
Inputs and settings
Provide prompt; use negative_prompt for specific exclusions. Adjust guidance_scale within 0–20 while holding the brief constant.
Use num_inference_steps from 1–50 and num_images from 1–4. Choose JPEG or PNG with output_format and keep seed for comparisons.
Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.
Supported inputs
These fields come from the current studio form for cogview4. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | — |
enable_safety_checker | On/off | Optional | — |
guidance_scale | Number | Optional | ≥ 0 · ≤ 20 |
negative_prompt | Text | Optional | — |
num_images | Whole number | Optional | ≥ 1 · ≤ 4 |
num_inference_steps | Whole number | Optional | ≥ 1 · ≤ 50 |
output_format | Text | Optional | jpeg, png |
seed | Whole number | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use CogView through the API.
Start with this model ID for the endpoint featured on this page:
cogview4
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.