Batch matrix-matrix and Dynamic Attention BMM applied a legacy Attention
processor to pipe.unet, which a diffusion transformer does not have, so
they served unet models alone and said nothing elsewhere. The choices, the
processor and its slice helper are removed, an unrecognized method now
warns rather than selecting nothing, and a stored value is rewritten to
Scaled-Dot-Product on load.
Reference entries for the bf16 repo and the sdnq uint4 quant load the
modular pipeline through the standard dispatch. Image tabs run the
model in still mode with audio off; the video tab keeps its own
overrides through the shared per-generation hook. Detailer is not
supported and is disabled with a warning.
The secondary unet loads from the networks panel toggle or the settings
page; companion ordering and dynamic visibility pushes in ui_settings.py
are not worth their footprint for one setting.
One UNET override cannot serve dual-transformer arches: ideogram4
conditional/unconditional and wan combined-stage experts need separate
files, and previously a single override landed on both experts.
- sd_unet_secondary option with per-slot tracking, consumed-state sync,
arch-change reset, and incompatible-override fallback
- dropdown renders beside the primary, follows it into quicksettings,
and is visible only for dual-transformer model types
- ideogram4 native single-file spec with a quant-aware fused-qkv
converter; such converters run before comfy_quant detection via
TransformerSpec.converter_handles_quant
- quicksettings render in configured order (sort keyed on the option
object and always fell back to alphabetical)
- post-load dtype warning skips quantized transformers
Krea 2 is a 12.9B single-stream flow-matching DiT trained from scratch, using a Qwen3-VL-4B text encoder and the Qwen-Image VAE. The transformer is vendored as a diffusers ModelMixin whose module tree mirrors the checkpoint, so weights load with no key conversion; the pipeline ports the reference encode, flow-matching denoise, and VAE decode. The text encoder is shared at runtime via the existing dedup registry, so Base and Turbo reuse one Qwen3-VL-4B copy.
Covers text-to-image, image-to-image, native LoRA, and the single-file UNET override. Also completes SD.Next's partial Qwen-Image VAE support (5D decode input and TAESD preview mapping) that K2 shares.
Register the subclass with generic.set_pipeline and build it with
from_pretrained, passing the SDNQ transformers and shared text encoder
while the vae, scheduler, and tokenizer load from the repo.
Diffusers-native port of the 9.3B flow-matching DiT: dual-transformer asymmetric CFG, a 13-layer Qwen3-VL tap encoder deduped with VQA and prompt-enhance, the Flux.2 VAE, and a logit-normal schedule. Loads a published bf16 repo with SDNQ at load.
Anima replaces the Cosmos T5-11B text encoder with Qwen3-0.6B + a
6-layer LLM adapter and uses CONST preconditioning instead of EDM.
- Add pipelines/model_anima.py loader with dynamic import of custom
AnimaTextToImagePipeline and AnimaLLMAdapter from model repo
- Register 'Anima' pipeline in shared_items.py
- Add name-based detection in sd_detect.py
- Fix list-format _class_name handling in guess_by_diffusers()
- Wire loader in sd_models.py load_diffuser_force()
- Skip noise_pred callback injection for Anima (uses velocity instead)
- Add output_type='np' override in processing_args.py
Add support for FLUX.2 Klein distilled models (4B and 9B variants):
- Add pipeline loader for Flux2KleinPipeline
- Add model detection for 'flux.2' + 'klein' patterns
- Add pipeline mapping in shared_items
- Add shared Qwen3ForCausalLM text encoder handling:
- 4B variants use Z-Image-Turbo's Qwen3-8B
- 9B variants use FLUX.2-klein-9B's Qwen3-14B
- Add reference entries for distilled (4B, 9B) and base models
- Update diffusers commit for Flux2KleinPipeline support
- Add GLM-Image (zai-org/GLM-Image) model detection and loading
- Custom pipeline loader with proper component handling:
- ByT5 text encoder (cannot use shared T5 due to different hidden size)
- Vision-language encoder (9B AR model)
- DiT transformer (7B)
- Fix EOS token early stopping in AR generation
- Add AR token generation progress tracking with terminal progress bar
- Fix uninitialized audio variable in processing
- Add TAESD support for GLM-Image (using f1 variant)
CalamitousFelicitousness
Vladimir Mandic
Disty0