github/InvokeAI
1
1
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI.git synced 2026-04-23 03:00:31 -04:00
Code Issues Packages Projects Releases Wiki Activity
Files
2425005aada012cfaf558aa609912c291d05bc29
InvokeAI/invokeai/backend/z_image
History
Alexander Eichhorn d7d051200f fix(z_image): use unrestricted image self-attention for regional prompting (#8718) 
Changes image self-attention from restricted (region-isolated) to unrestricted
(all image tokens can attend to each other), similar to the FLUX approach.

This fixes the issue where ZImage-Turbo with multiple regional guidance layers
would generate two separate/disconnected images instead of compositing them
into a single unified image.

The regional text-image attention remains restricted so that each region still
responds to its corresponding prompt.

Fixes #8715
2025-12-28 11:32:50 -05:00
..
extensions
fix(z_image): use unrestricted image self-attention for regional prompting (#8718)
2025-12-28 11:32:50 -05:00
__init__.py
Feature: Add Z-Image-Turbo regional guidance (#8672)
2025-12-26 02:25:38 +00:00
text_conditioning.py
Feature: Add Z-Image-Turbo regional guidance (#8672)
2025-12-26 02:25:38 +00:00
z_image_control_adapter.py
style: apply ruff formatting
2025-12-21 18:52:12 +01:00
z_image_control_transformer.py
style: apply ruff formatting
2025-12-21 18:52:12 +01:00
z_image_controlnet_extension.py
chore: format code for ruff checks
2025-12-23 01:04:22 +05:30
z_image_patchify_utils.py
chore: format code for ruff checks
2025-12-23 01:04:22 +05:30
z_image_transformer_patch.py
Feature: Add Z-Image-Turbo regional guidance (#8672)
2025-12-26 02:25:38 +00:00