{
  "model_name": "Anima Regional ControlNet-LLLite",
  "filename": "anima_regional_4335.safetensors",
  "sha256": "e907ea9259b324a11c94e5767420a6a46c6a9d86597df5ccf9b1ad5eeb817618",
  "file_size_bytes": 51133584,
  "training_base": {
    "name": "Anima-Base v1.0",
    "repository": "circlestone-labs/Anima",
    "file_sha256": "bd43b7cffe1ed1153d9c41e7beb2f18cb1273eafbaa3af3edd6a173dc90a006e"
  },
  "conditioning": {
    "input_channels": 3,
    "type": "RGB instance-color region map",
    "background_rgb": [
      0,
      0,
      0
    ],
    "colors": "random per image and instance; no fixed semantic color IDs",
    "inpaint_masked_input": false
  },
  "architecture_metadata": {
    "lllite.target_layers": "self_attn_q_pre,self_attn_kv_pre",
    "lllite.target_atomics": "self_attn_q_pre,self_attn_kv_pre",
    "lllite.cond_dim": "128",
    "lllite.version": "2",
    "modelspec.resolution": "1024x1024",
    "lllite.cond_resblocks": "4",
    "lllite.cond_in_channels": "3",
    "lllite.use_aspp": "true",
    "modelspec.architecture": "anima-preview/control-net-lllite",
    "modelspec.implementation": "https://huggingface.co/circlestone-labs/Anima",
    "modelspec.prediction_type": "epsilon",
    "lllite.cond_emb_dim": "64",
    "modelspec.sai_model_spec": "1.0.1",
    "lllite.mlp_dim": "64",
    "modelspec.title": "anima_regional_4335",
    "modelspec.implementation_version": "sd-scripts/690ea7f96c23182352ec63def76d431c6120bd2f",
    "lllite.aspp_dilations": "1,2,4,8",
    "lllite.inpaint_masked_input": "false",
    "modelspec.date": "2026-10-11T03:29:17"
  },
  "trainable_parameters": 25517504,
  "tensor_count": 828,
  "trainer": {
    "repository": "https://github.com/kohya-ss/sd-scripts",
    "commit": "690ea7f96c23182352ec63def76d431c6120bd2f",
    "entrypoint": "anima_train_control_net_lllite.py"
  },
  "hardware": "1 NVIDIA RTX PRO 6000 Blackwell Server Edition (96 GB)",
  "software": {
    "python": "3.12",
    "pytorch": "2.8.0+cu128",
    "cuda": "12.8",
    "accelerate": "1.15.0",
    "bitsandbytes": "0.50.2",
    "diffusers": "0.40.0",
    "transformers": "5.17.0",
    "safetensors": "0.8.0"
  },
  "completed_steps": 4335,
  "main_stage_elapsed_seconds": 44083.32825228525,
  "main_stage_elapsed_hours": 12.245368958968125,
  "native_progress_elapsed": "12:12:06",
  "timing_scope": "Main stage includes initialization and final save; excludes earlier installation, initial caching, smoke/resume tests and batch benchmarks.",
  "native_final_average_loss": 0.0786,
  "loss_does_not_establish_generation_quality": true,
  "actual_training_parameters": {
    "save_model_as": "safetensors",
    "save_precision": "bf16",
    "cond_emb_dim": 64,
    "lllite_cond_dim": 128,
    "lllite_mlp_dim": 64,
    "lllite_cond_resblocks": 4,
    "lllite_use_aspp": true,
    "lllite_cond_in_channels": 3,
    "lllite_inpaint_masked_input": false,
    "lllite_target_layers": "self_attn_q_pre,self_attn_kv_pre",
    "lllite_multiplier": 1.0,
    "learning_rate": 0.0001,
    "optimizer_type": "AdamW8bit",
    "lr_scheduler": "constant_with_warmup",
    "timestep_sampling": "shift",
    "discrete_flow_shift": 3.0,
    "save_state": true,
    "mixed_precision": "bf16",
    "gradient_checkpointing": true,
    "cache_latents": true,
    "cache_latents_to_disk": true,
    "cache_text_encoder_outputs": true,
    "cache_text_encoder_outputs_to_disk": true,
    "vae_batch_size": 4,
    "text_encoder_batch_size": 8,
    "vae_chunk_size": 64,
    "vae_disable_cache": true,
    "qwen_image_vae_2d": true,
    "attn_mode": "torch",
    "max_data_loader_n_workers": 4,
    "gradient_accumulation_steps": 1,
    "max_grad_norm": 1.0,
    "seed": 20261010,
    "qwen3_max_token_length": 512,
    "t5_max_token_length": 512,
    "log_with": "tensorboard",
    "save_state_on_train_end": true,
    "lr_warmup_steps": 58,
    "lllite_dropout": 0.0,
    "optimizer_args": [
      "weight_decay=0.01",
      "betas=0.9,0.999",
      "eps=1e-8"
    ],
    "loss_type": "l2",
    "cuda_allow_tf32": true,
    "cuda_cudnn_benchmark": false,
    "max_train_steps": 4335,
    "save_every_n_steps": 144,
    "sample_every_n_steps": 289,
    "sample_at_first": true,
    "persistent_data_loader_workers": true,
    "published_filename": "anima_regional_4335.safetensors"
  },
  "dataset": {
    "repo_id": "toyxyz/booruregion_10k",
    "revision": "7f3418e46677688b846364ce6f7de170027d424d",
    "manifest_sha256": "5bdfb489e19b746922255742e18e5d67114645fbae11847ba16c894f6f85a38c",
    "split_source_counts": {
      "test": {
        "danbooru_original": 39,
        "anima_generated": 81
      },
      "train": {
        "danbooru_original": 3834,
        "anima_generated": 6166
      },
      "validation": {
        "danbooru_original": 32,
        "anima_generated": 88
      }
    },
    "total_pairs": 10240,
    "train_pairs": 10000,
    "resolution_groups": 109,
    "enable_bucket": false,
    "caption_dropout_rate": 0.15,
    "shuffle_caption": false,
    "flip_aug": false,
    "color_aug": false,
    "random_crop": false,
    "tag_dropout_rate": 0.0
  },
  "batch_accounting": {
    "batch_size_setting": 32,
    "batches_per_epoch": 378,
    "mean_images_per_batch": 26.455026455026456,
    "nominal_step_times_batch": 138720,
    "estimated_effective_image_exposures": 114682.53968253969,
    "exposure_estimate_method": "steps multiplied by epoch-average images per batch; not an observed per-image count"
  },
  "validation": {
    "fixed_cases": 6,
    "sample_steps": 30,
    "cfg": 4,
    "flow_shift": 3,
    "same_seed_multiplier_comparison": [
      0,
      1
    ],
    "sample_every_n_steps": 289,
    "held_out_test_set_quantitative_evaluation": false
  },
  "inference_settings_used_in_comfyui_comparison": {
    "node": "AnimaLLLiteApply_sdscripts",
    "strength": 1.0,
    "start_percent": 0.0,
    "end_percent": 1.0,
    "preserve_wrapper": true,
    "steps": 30,
    "cfg": 4,
    "sampler": "er_sde",
    "scheduler": "simple",
    "denoise": 1.0,
    "seed": 12321312312313
  },
  "release_date": "2026-10-11"
}