You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
[MiniMax-H3] Load the pruned ComfyUI checkpoints and add single-file support for MiniMax-H3-Image #15302
The pruned files replace the timestep MLP and the wide AdaLN projections (about 40% of the parameters) with the activated timestep curve sampled on a 1025-point grid (adaln_t_table) and 8-input AdaLN projections. MiniMaxH3Transformer3DModel has no module that matches these weights, and from_single_file refuses adaln_t_table.
MiniMaxH3ImageTransformer2DModel has no single-file support at all (no FromOriginalModelMixin), and the ComfyUI file stores the PDD heads as a stacked bank (head 0 plus per-step offsets) rather than as pdd_proj_out.{i}.
Describe the solution you'd like.
An opt-in config field (adaln_curve_grid) on both transformers. When set, time_embedder is a lookup of the sampled curve, linearly interpolated as ComfyUI does, and the AdaLN projections skip their SiLU. Stock configs keep their current behaviour.
from_single_file for both transformers: map adaln_t_table to the table, unstack the PDD head bank for the image model, and refuse quantized ComfyUI files with a message naming the bf16 file.
The repository config on the Hub describes the unpruned model, and no Hub repo carries a pruned diffusers config that a model type could point at. So the pruned shape (adaln_curve_grid, time_embed_dim) has to be read off the checkpoint itself. #15299 does this with a new optional key in the single-file registry, config_from_checkpoint_fn. Is a new registry key acceptable here, or would you prefer another route (for example a separate model type with its own config)?
Activity