Skip to content

[建议 / Feature] Feature Request (chat.z.ai): Improve AI image generation — higher resolution, larger sizes, and outpainting #1273

Open

Description

提交前确认 · Pre-submission checklist

  • 我已搜索过现有 issue,确认这不是重复提议 / I searched existing issues and confirmed this isn't a duplicate.
  • 我已阅读 CONTRIBUTING.md / I've read CONTRIBUTING.md.

问题类别 · Category

UI / 界面体验 · UI / UX

涉及的 Agent 框架 · Agent framework

不涉及框架 · Not framework-specific

使用场景 · Use case

Summary
Image generation in chat.z.ai (GLM-Image) has improved a lot — especiallytext rendering inside images. However, for real design work it still lacksa few capabilities that competing tools already offer. I would like torequest the following enhancements.

Requested features
Higher resolution output — Add 2K/4K output options (or a simple"Quality: Standard / High" toggle) beyond the current default sizes.
Larger / custom sizes — Allow custom dimensions or larger presets(e.g., print-ready A4, wide banners), with aspect-ratio controldirectly in the UI (16:9, 3:4, etc.).
Built-in outpainting (frame expansion) — A one-click "Expand image"action that extends a generated or uploaded image beyond its originalborders. Very useful for wallpapers, banners, and converting portraitimages to landscape without losing the subject.
Built-in upscaling (bonus) — An "Upscale" button on any generatedimage, with detail-preserving enhancement (faces, small text, textures).
Why it matters
Users now generate images directly for documents, slides and websites,especially since the new Cloud panel keeps generated files organized.
Today we must export to third-party upscalers/outpainting tools, whichbreaks the workflow and usually destroys the text that GLM-Image rendersso accurately.
Competing assistants already ship similar controls, and this is one ofthe most common asks in design-oriented workflows.
Current behavior
A fixed set of standard output sizes; no resolution or quality selector.
No built-in way to expand an image beyond its frame; re-prompting for a"wider" version regenerates the whole composition instead of extending it.
Suggested UX
A small options row under the prompt box: aspect ratio + size/quality.
"Expand" and "Upscale" actions on any generated image (or in the Cloudfile panel), keeping the original pixels and only generating the newborder area to preserve GLM-Image's excellent text rendering.
Environment
Platform: chat.z.ai (web, latest version)
Date: 2026-10-28
Happy to beta-test any of these features. Thank you for the new Cloudpanel — it is already a big improvement! 🙏

建议方案 · Proposal

"Related: #687, #310 (different scope)

预期价值 · Expected value

No response

你认为的优先级 · Your perceived priority

No response

你使用的 ZCode 版本 / 环境 · ZCode version / environment

No response

补充材料 · Additional context

No response

Activity

  1. github-actions commented on Oct 28, 2026

    @github-actions

    👋 感谢你的反馈,我们已经收到。

    • 维护者看到后会尽快回复你。
    • 状态保持为 status: 待评估,你可以随时补充信息。
    • 信息不全时我们会打上 needs: 更多信息 标签并 @ 你。

    👋 Thanks — we've received your issue.

    • A maintainer will get back to you as soon as we can.
    • Status stays at status: 待评估 (Triage); feel free to add context.
    • If we need more details, we'll add needs: 更多信息 and ping you.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions