Ctrl + C ; Ctrl + V

(Neta-Lumina)

backend/huggingface/nvidia/PiD/model_index.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "Lumina2Pipeline",
+  "_diffusers_version": "0.35.0.dev0",
+  "_name_or_path": "neta-lumina-v1.0",
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "Gemma2Model"
+  ],
+  "tokenizer": [
+    "transformers",
+    "GemmaTokenizerFast"
+  ],
+  "transformer": [
+    "diffusers",
+    "Lumina2Transformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

backend/huggingface/nvidia/PiD/scheduler/scheduler_config.json

@@ -0,0 +1,16 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.33.0.dev0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_sigmas": false,
+  "max_image_seq_len": 4096,
+  "max_shift": 1.15,
+  "num_train_timesteps": 1000,
+  "shift": 6.0,
+  "shift_terminal": null,
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": false,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

backend/huggingface/nvidia/PiD/text_encoder/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/gemma-2-2b",
+  "architectures": [
+    "Gemma2Model"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": 50.0,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2304,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 256000
+}

backend/huggingface/nvidia/PiD/tokenizer/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

backend/huggingface/nvidia/PiD/transformer/config.json

@@ -0,0 +1,28 @@
+{
+  "_class_name": "Lumina2Transformer2DModel",
+  "_diffusers_version": "0.35.0.dev0",
+  "axes_dim_rope": [
+    32,
+    32,
+    32
+  ],
+  "axes_lens": [
+    300,
+    512,
+    512
+  ],
+  "cap_feat_dim": 2304,
+  "ffn_dim_multiplier": null,
+  "hidden_size": 2304,
+  "in_channels": 16,
+  "multiple_of": 256,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 24,
+  "num_kv_heads": 8,
+  "num_layers": 26,
+  "num_refiner_layers": 2,
+  "out_channels": null,
+  "patch_size": 2,
+  "sample_size": 128,
+  "scaling_factor": 1.0
+}

backend/huggingface/nvidia/PiD/vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.33.0.dev0",
+  "_name_or_path": "black-forest-labs/FLUX.1-dev",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 16,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.3611,
+  "shift_factor": 0.1159,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": false,
+  "use_quant_conv": false
+}