Base ships last.up all-zeros so the branch is a no-op; pre-branch
finetunes omit both keys. A zero_init_missing spec field zero-fills
them on load instead of falling back to the base transformer.
strptime was handed the stat datetime instead of the date string, so it
always failed and left a raw string mtime; the Date sort then crashed on
mixed str/datetime items. Parse the date string, falling back to stat mtime.
CivitAI has no model type for a standalone transformer, so DiT finetunes
are published as 'Checkpoint' like full models and all landed in
Stable-diffusion, where the single-file transformer loader never looks.
Route Checkpoint downloads to UNET unless the base model is a known full
checkpoint (SD1.x/2.x, SDXL and its Pony/Illustrious/NoobAI derivatives,
SVD, Kolors, Stable Cascade). Downloads with no base_model, or a
civitai_save_type_folders override, keep the previous behavior.
An absolute 1024-byte floor rejected valid complete downloads, since
some safetensors are legitimately tiny (a lone projector-diff tensor is
~160 bytes). Verify completeness against the declared Content-Length
instead, accepting any size, and keep the floor only as a fallback when
it is missing. Reject text/* responses up front so an HTML error or
login page served with HTTP 200 is never saved as a model file.
The LTX tab already collected a last-frame image but anchored every condition at index 0, so it never acted as a last frame. Build a separate condition for it at the final frame: index -1 for the 2.x family (latent index, negatives wrap) and num_frames-1 for 0.9 (pixel index). The Last image input now shows only for Condition models, the pipelines that accept multi-frame conditioning.
The I2V path forwards a last-frame image to the pipeline when one is supplied and the loaded pipeline accepts it, turning the run into first-last-frame interpolation. supports_last_frame() gates on the pipeline taking a last_image argument and not running expand_timesteps, which conditions on the first frame only, so a model that cannot use a last frame logs a warning instead of silently ignoring it.
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.
CalamitousFelicitousness
Disty0
Vladimir Mandic
Oleksandr Liutyi