invoke-ai/InvokeAI

[enhancement]: Suggestion to improve the Hires Fix logic for SD 1.5.

Open

#6,572 opened on 2024年7月3日

GitHub で見る
 (13 comments) (1 reaction) (0 assignees)TypeScript (20,358 stars) (2,164 forks)batch import
enhancementgood first issue

説明

Is there an existing issue for this?

  • I have searched the existing issues

Contact Details

No response

What should this feature add?

When I generate images at 1024x1536 (2:3), the initial image is generated at 416 x 624. Here, the resolution of smaller side goes way below 512 pixels, which is not an ideal resolution for SD 1.5 finetunes since the majority are trained on images above 512 pixels and can work perfectly fine up to 768 x 768. Please modify the Hires Fix logic to generate the initial image with a minimum resolution of 512 on the smaller side. For example, if the dimensions specified by the user are 1024 x 1536 (2:3), the resolution of the initial image generated should be 512 x 768. Fallback to the current logic only when the larger side of the initial image exceeds 768 pixels, which will only happen at some aspect ratios like 16:9 or 1:2 that are quite uncommon in SD community.

Alternatives

No response

Additional Content

No response

コントリビューターガイド

技術スタック
pythontypescript
領域
aimachine learning
Issue 種別
feature
難度新しい貢献者にとっての実装難度です。1 は非常に小さな変更、5 は専門的な作業です。
3
推定時間経験ある貢献者が調査、実装、テスト、pull request 準備にかけるおおよその時間範囲です。
half day
活動状況Issue が今どれだけ取り組みやすいかを示します。新しい、活発、古い、ブロック中、またはメンテナー入力待ちなどです。
active
明確さ期待される変更、受け入れ条件、次の手順がどれだけ明確かを示します。
clear
前提条件
Basic understanding of Stable DiffusionFamiliarity with InvokeAI's Hires Fix functionality
初心者向け度初回貢献者にどれだけ取り組みやすいかを 1-100 で推定したスコアです。
60
調査方針
Start by examining the current Hires Fix implementation in InvokeAI, likely in the image generation pipeline. Look for functions that compute initial image dimensions based on target dimensions. Check the GitHub issue comments for any maintainer guidance or code references. Consider how to enforce a minimum resolution of 512 on the smaller side while respecting the 768 cap on the larger side.