InvokeAI

mirror of https://github.com/invoke-ai/InvokeAI.git synced 2026-01-15 06:38:10 -05:00

Files

psychedelicious a44bfb4658 fix(mm): handle FLUX models w/ diff in_channels keys

Before FLUX Fill was merged, we didn't do any checks for the model variant. We always returned "normal".

To determine if a model is a FLUX Fill model, we need to check the state dict for a specific key. Initially, this logic was too strict and rejected quantized FLUX models. This issue was resolved, but it turns out there is another failure mode - some fine-tunes use a different key.

This change further reduces the strictness, handling the alternate key and also falling back to "normal" if we don't see either key. This effectively restores the previous probing behaviour for all FLUX models.

Closes #7856
Closes #7859

2025-03-31 12:32:55 +11:00

controlnet

Remove instantx_control_mode from FLUX ControlNet node.

2024-10-09 22:00:54 +00:00

extensions

Add support for FLUX Redux masks.

2025-03-06 10:31:17 +11:00

ip_adapter

Infer the clip_extra_context_tokens param from the state dict for FLUX XLabs IP-Adapter V2 models.

2024-11-18 17:06:53 -08:00

modules

Normalize the T5 model identifiers so that a FLUX T5 or an SD3 T5 model can be used interchangeably.