InvokeAI

mirror of https://github.com/invoke-ai/InvokeAI.git synced 2026-04-23 03:00:31 -04:00

Files

Alexander Eichhorn 0ae7392c81 fix(model_manager): detect Flux1/2 VAE by latent space dimensions instead of filename (#8790 )

* fix(model_manager): detect Flux VAE by latent space dimensions instead of filename

VAE detection previously relied solely on filename pattern matching, which failed
for Flux VAE files with generic names like "ae.safetensors". Now probes the model's
decoder.conv_in weight shape to determine the latent space dimensions:
- 16 channels -> Flux VAE
- 4 channels -> SD/SDXL VAE (with filename fallback for SD1/SD2/SDXL distinction)

* fix(model_manager): add latent space probing for Flux2 VAE detection

Extend Flux2 VAE detection to also check for 32-dimensional latent space
(decoder.conv_in with 32 input channels) in addition to BatchNorm layers.
This provides more robust detection for Flux2 VAE files regardless of filename.

* Chore Ruff format

---------

Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>

2026-01-27 05:20:50 +00:00

flux

Feature: Add DyPE (Dynamic Position Extrapolation) support to FLUX models for improved high-resolution image generation (#8763 )

2026-01-26 23:54:44 -05:00

flux2

feat(flux2): add FLUX.2 klein model support (#8768 )

2026-01-26 23:21:37 -05:00

image_util

Implement PBR Maps Node (#8700 )

2025-12-29 02:11:46 +00:00

ip_adapter

ruff format