The FLUX and SDXL loaders know their architecture's block names up front, which does not scale across ComfyUI's ~99 model configs. The new Universal node discovers a model's block layout at runtime instead: stack names, stack sizes and their execution order all come from the loaded model, so pruned, distilled and brand-new architectures work without a code change. Concatenating the discovered stacks puts every block on one normalised depth axis, split into five buckets, alongside embeddings, output head and text encoder. Covers SD1.5/2/3, SDXL, FLUX, Chroma, AuraFlow, PixArt, HiDream, Qwen-Image, Wan, LTX-Video, Mochi, HunyuanVideo/DiT, Lumina and Cosmos. Verified against real ComfyUI: models built from ComfyUI's own configs on the meta device plus its *_to_diffusers key tables, 8000+ authentic state-dict keys across 11 architectures, none falling through to "Other Tensors". That pass found and fixed real gaps: SD3's negative "joint_blocks.-1" index, Lumina's noise_refiner/context_refiner stacks, AuraFlow's native double_layers naming, several conditioning embedders, and FLUX's ControlNet pos_embed_input. No widget was added, removed or reordered on the FLUX or SDXL nodes, so existing workflows are unaffected. Bumps version to 1.2.0.
15 lines
699 B
TOML
15 lines
699 B
TOML
[project]
|
|
name = "Bobs_LoRA_Loader"
|
|
description = "Block-weighted LoRA loaders for ComfyUI. Dedicated SDXL and FLUX nodes plus a Universal node that discovers any supported architecture's block layout at runtime (SD1.5/2/3, Chroma, AuraFlow, PixArt, HiDream, Qwen-Image, Wan, LTX-Video, Mochi, HunyuanVideo, Lumina, Cosmos and more). Presets for common use-cases like 'Character' and 'Style', plus a 'Custom' mode for per-block control."
|
|
version = "1.2.0"
|
|
license = {file = "LICENSE"}
|
|
|
|
[project.urls]
|
|
Repository = "https://github.com/BobsBlazed/Bobs-Lora-Loader"
|
|
# Used by Comfy Registry https://comfyregistry.org
|
|
|
|
[tool.comfy]
|
|
PublisherId = "bobsblazed"
|
|
DisplayName = "Bobs_LoRA_Loader"
|
|
Icon = ""
|