Alexander Eichhorn c83f29362e fix(flux2-vae): support FLUX.2 small-decoder VAE variant (#9032) ...

Infer encoder and decoder block_out_channels independently from the
state dict and rebuild the decoder submodule when its channel widths
differ from the encoder, so the asymmetric full_encoder_small_decoder
checkpoint from black-forest-labs/FLUX.2-small-decoder loads correctly.

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

2026-04-20 21:58:16 -04:00

..

anima

feat: add Anima model support (#8961)

2026-04-09 12:04:11 -04:00

flux

Broaden text encoder partial-load recovery (#9034)

2026-04-09 20:09:40 -04:00

flux2

fix(flux2): Fix FLUX.2 Klein image generation quality (#8838)

2026-02-06 00:34:54 -05:00

image_util

External models (Gemini Nano Banana & OpenAI GPT Image) (#8633) (#8884)

2026-04-20 17:13:26 +00:00

ip_adapter

ruff format

2025-09-18 11:05:32 +10:00

model_hash

Run ruff

2024-06-26 21:46:59 +10:00

model_manager

fix(flux2-vae): support FLUX.2 small-decoder VAE variant (#9032)

2026-04-20 21:58:16 -04:00

onnx

fix(backend): revert non-blocking device transfer

2024-07-16 08:59:42 +10:00

patches

Fix Z-Image LoRA detection for Kohya and ComfyUI formats (#9007)

2026-04-21 00:28:10 +00:00

quantization

fix(gguf): ensure dequantized tensors are on correct device for MPS (#8713)

2026-01-02 00:45:50 +00:00

rectified_flow

chore:ruff

2025-05-27 07:28:47 +10:00

sig_lip

feat(mm): siglip model loading supports partial loading

2025-04-18 10:12:03 +10:00

stable_diffusion

Feat[model support]: Qwen Image — full pipeline with edit, generate LoRA, GGUF, quantization, and UI (#9000)

2026-04-12 14:39:13 +02:00

tiles

feat(nodes): extract LATENT_SCALE_FACTOR to constants.py

2024-03-01 10:42:33 +11:00

util

fix: remove directory entry sizes from directory_size() to report accurate file totals (#9040)

2026-04-21 01:00:19 +00:00

z_image

fix(z_image): use unrestricted image self-attention for regional prompting (#8718)

2025-12-28 11:32:50 -05:00

__init__.py

consolidate model manager parts into a single class

2024-03-01 10:42:33 +11:00

llava_onevision_pipeline.py

feat(mm): llava model loading supports partial loading; fix OOM crash on initial load

2025-04-18 10:12:03 +10:00

model_patcher.py

refactor: model manager v3 (#8607)

2025-10-15 10:18:53 +11:00

raw_model.py

Merge branch 'main' into ryan/spandrel-upscale

2024-07-16 15:14:08 -04:00

spandrel_image_to_image_model.py

Add tiling support to the SpoandrelImageToImage node.

2024-07-10 14:25:19 -04:00

textual_inversion.py

Add util functions calc_tensor_size(...) and calc_tensors_size(...).

2024-09-15 04:39:56 +03:00