sparse1024/dit/config.json

{
  "model_type": "sparse_dit",
  "model_class": "pixal3d.models.transformers.sparse_dit.SparseDiTDenoiser",
  "resolution": 128,
  "in_channels": 16,
  "out_channels": 16,
  "model_channels": 1024,
  "cond_channels": 1024,
  "num_blocks": 24,
  "num_heads": 32,
  "num_kv_heads": 2,
  "compression_block_size": 4,
  "selection_block_size": 8,
  "topk": 8,
  "compression_version": "v2",
  "pe_mode": "ape",
  "factor": 0.5,
  "sparse_conditions": true,
  "qk_rms_norm": true,
  "use_shift": true,
  "use_checkpoint": true,
  "use_fp16": false,
  "use_visual_condition": true,
  "visual_condition_dim": 1024,
  "image_attn_mode": "proj"
}