vae

AutoencoderKL

cpu

torch.bfloat16

83819683

241

FrozenDict({'in_channels': 3, 'out_channels': 3, 'down_block_types': ['DownEncoderBlock2D', 'DownEncoderBlock2D', 'DownEncoderBlock2D', 'DownEncoderBlock2D'], 'up_block_types': ['UpDecoderBlock2D', 'UpDecoderBlock2D', 'UpDecoderBlock2D', 'UpDecoderBlock2D'], 'block_out_channels': [128, 256, 512, 512], 'layers_per_block': 2, 'act_fn': 'silu', 'latent_channels': 16, 'norm_num_groups': 32, 'sample_size': 1024, 'scaling_factor': 0.3611, 'shift_factor': 0.1159, 'latents_mean': None, 'latents_std': None, 'force_upcast': True, 'use_quant_conv': False, 'use_post_quant_conv': False, 'mid_block_add_attention': True, '_class_name': 'AutoencoderKL', '_diffusers_version': '0.30.0.dev0', '_name_or_path': '/mnt/models/Diffusers/models--HiDream-ai--HiDream-I1-Dev/snapshots/0fad2ea0ccf9a80ddf019ea777eedb27c1ccb232/vae'})

text_encoder

CLIPTextModelWithProjection

xpu:0

torch.bfloat16

123781632

153

CLIPTextConfig { "architectures": [ "CLIPTextModelWithProjection" ], "attention_dropout": 0.0, "bos_token_id": 0, "dropout": 0.0, "eos_token_id": 2, "hidden_act": "quick_gelu", "hidden_size": 768, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-05, "max_position_embeddings": 248, "model_type": "clip_text_model", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 1, "projection_dim": 768, "torch_dtype": "bfloat16", "transformers_version": "4.52.4", "vocab_size": 49408 }

text_encoder_2

CLIPTextModelWithProjection

xpu:0

torch.bfloat16

694840320

393

CLIPTextConfig { "architectures": [ "CLIPTextModelWithProjection" ], "attention_dropout": 0.0, "bos_token_id": 0, "dropout": 0.0, "eos_token_id": 2, "hidden_act": "gelu", "hidden_size": 1280, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 5120, "layer_norm_eps": 1e-05, "max_position_embeddings": 218, "model_type": "clip_text_model", "num_attention_heads": 20, "num_hidden_layers": 32, "pad_token_id": 1, "projection_dim": 1280, "torch_dtype": "bfloat16", "transformers_version": "4.52.4", "vocab_size": 49408 }

text_encoder_3

T5EncoderModel

cpu

torch.bfloat16

4762310656

463

T5Config { "architectures": [ "T5EncoderModel" ], "classifier_dropout": 0.0, "d_ff": 10240, "d_kv": 64, "d_model": 4096, "decoder_start_token_id": 0, "dense_act_fn": "gelu_new", "dropout_rate": 0.1, "eos_token_id": 1, "feed_forward_proj": "gated-gelu", "initializer_factor": 1.0, "is_encoder_decoder": true, "is_gated_act": true, "layer_norm_epsilon": 1e-06, "model_type": "t5", "num_decoder_layers": 24, "num_heads": 64, "num_layers": 24, "output_past": true, "pad_token_id": 0, "relative_attention_max_distance": 128, "relative_attention_num_buckets": 32, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.52.4", "use_cache": true, "vocab_size": 32128 }

text_encoder_4

LlamaForCausalLM

cpu

torch.bfloat16

8030261248

423

LlamaConfig { "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [ 128001, 128008, 128009 ], "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "output_attentions": true, "output_hidden_states": true, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3" }, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.52.4", "use_cache": true, "vocab_size": 128256 }

tokenizer

CLIPTokenizer

0

0

None

tokenizer_2

CLIPTokenizer

0

0

None

tokenizer_3

T5Tokenizer

0

0

None

tokenizer_4

PreTrainedTokenizerFast

0

0

None

scheduler

FlowMatchLCMScheduler

0

0

FrozenDict({'num_train_timesteps': 1000, 'shift': 6.0, 'use_dynamic_shifting': False, 'base_shift': 0.5, 'max_shift': 1.15, 'base_image_seq_len': 256, 'max_image_seq_len': 4096, 'invert_sigmas': False, 'shift_terminal': None, 'use_karras_sigmas': False, 'use_exponential_sigmas': False, 'use_beta_sigmas': False, 'time_shift_type': 'exponential', 'scale_factors': None, 'upscale_mode': 'bicubic', '_class_name': 'FlowMatchLCMScheduler', '_diffusers_version': '0.34.0.dev0'})

transformer

HiDreamImageTransformer2DModel

xpu:0

torch.bfloat16

17105733184

2090

FrozenDict({'patch_size': 2, 'in_channels': 16, 'out_channels': 16, 'num_layers': 16, 'num_single_layers': 32, 'attention_head_dim': 128, 'num_attention_heads': 20, 'caption_channels': [4096, 4096], 'text_emb_dim': 2048, 'num_routed_experts': 4, 'num_activated_experts': 2, 'axes_dims_rope': [64, 32, 32], 'max_resolution': [128, 128], 'llama_layers': [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31, 31], 'force_inference_output': False, '_use_default_values': ['force_inference_output'], '_class_name': 'HiDreamImageTransformer2DModel', '_diffusers_version': '0.32.1', '_name_or_path': 'HiDream-ai/HiDream-I1-Dev'})

_name_or_path

str

0

0

None

_class_name

str

0

0

None

_diffusers_version

str

0

0

None

Time: 39m 13.08s
pipeline 2315.96 move 22.51 prompt 22.46 te 20.28 decode 14.57 offload 12.04
GPU 37942 MB 30% | RAM 58.6 GB 47%

Steps: 50| Size: 1024x1024| Seed: 2423417735| CFG scale: 2|
Model: HiDream-I1-Full| App: SD.Next| Version: 72eb013|
Operations: txt2img| Pipeline: HiDreamImagePipeline