The core took reference images only, so no api caller could send the video and
audio references the ref2va workflow conditions on, and the marshalling that
handles them existed solely in the MiniMax tab.
validate_references now gates on the workflow and hands the entries to the
architecture that owns them, which accepts decoded images and local file paths
in any mix and preserves their order, since order fixes the labels a prompt
addresses. reference_caps exposes the same limits the validation enforces, so a
client reads them instead of mirroring the numbers.
- MAX_IMAGE_REFERENCES is gone: the limits now cover all three kinds and a total
- the run body no longer builds reference objects or knows their class
- an image is converted where it is built rather than at the call site, so a
reference decoded from a file and one posted as base64 arrive the same way
- pipeline args summarize a reference list by kind, since a decoded video would
otherwise print its frames into the per-generation log line
- the video endpoint documents what it actually accepts: images alone, because
video and audio decode from files rather than from the wire, and an upload
reference only where an extension provides the store that resolves one
An empty prompt tokenizes to zero tokens and the conditioner fails
reshaping an empty sequence; a single space keeps the generate-on-empty
behavior other models have.
First natively modular model: the pipeline is driven directly through
ModularPipeline, with components fetched per workflow (fl2va covers
text and first/last-frame conditioning).
- per-generation overrides snap the canvas to /32, align frames to
the 17n+5 grid and duration window, and keep the bespoke scheduler
pair
- group offload for modular pipelines applied per component in
sd_offload; re-application is a guarded no-op
- audio checkbox pops the audio decode block so decode and muxing are
skipped
- frames=1 renders a single still image: the duration floor lifts per
instance and sub-floor latents pad at the vae decoder
- progress and interrupt handling via a transformer forward pre-hook
- vae scale factor override, tuple-safe patch size
Network activation ran after prompt encoding, so text encoder lora
weights never affected embeds on the first generation and the stale
result was then served from the embed cache. The trailing unfiltered
activate in network_load also overrode the te exclude filter, so the
lora_apply_te setting was never honored.
- parse and activate networks in process_base before pipeline args are built
- activate_filtered gates text encoder components on per-request or global
lora_apply_te; used by base, hires, detailer and faceid call sites
- network_load accepts activate=False for callers that run their own
deactivate/activate sequence with include/exclude
- network_activate walks excluded components in restore-only mode so a
filtered text encoder reverts to backup instead of keeping stale deltas
- loaded_loras cache is single-entry since per-filter entries go stale when
the setting toggles
- prompt embed cache key includes the effective lora_apply_te value
Wan 2.2 A14B ships a per-model boundary_ratio (0.9 I2V, 0.875 T2V) that selects the high- or low-noise expert per step. The video and base-model image loaders both load the shipped value; the slider override is applied at generation time in set_pipeline_args, the one point both paths pass through before invoking the pipeline.
The denoising loop reads config.boundary_ratio each call, so tuning takes effect with no reload for video and base-model images alike. The slider defaults to -1, meaning use the model's value; 0 to 1 set the boundary explicitly. Single-expert stages stay load-time because they drop a transformer to free VRAM.
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 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
QualiaRain