add hunyuan 2.1

2025-06-19 00:57:35 +03:00
parent 4e33b6736d
commit c76b1a25b7
127 changed files with 72259 additions and 2 deletions
@@ -0,0 +1,82 @@
+model:
+  target: hy3dshape.models.denoisers.hunyuandit.HunYuanDiTPlain
+  params:
+    input_size: &num_latents 4096
+    in_channels: 64
+    hidden_size: 2048
+    context_dim: 1024
+    depth: 21
+    num_heads: 16
+    qk_norm: true
+    text_len: 1370
+    with_decoupled_ca: false
+    use_attention_pooling: false
+    qk_norm_type: 'rms'
+    qkv_bias: false
+    use_pos_emb: false
+    num_moe_layers: 6
+    num_experts: 8
+    moe_top_k: 2
+
+vae:
+  target: hy3dshape.models.autoencoders.ShapeVAE
+  params:
+    num_latents: *num_latents
+    embed_dim: 64
+    num_freqs: 8
+    include_pi: false
+    heads: 16
+    width: 1024
+    num_encoder_layers: 8
+    num_decoder_layers: 16
+    qkv_bias: false
+    qk_norm: true
+    scale_factor: 1.0039506158752403
+    geo_decoder_mlp_expand_ratio: 4
+    geo_decoder_downsample_ratio: 1
+    geo_decoder_ln_post: true
+    point_feats: 4
+    pc_size: 81920
+    pc_sharpedge_size: 0
+
+conditioner:
+  target: hy3dshape.models.conditioner.SingleImageEncoder
+  params:
+    main_image_encoder:
+        type: DinoImageEncoder # dino large
+        kwargs:
+            config:
+              attention_probs_dropout_prob: 0.0
+              drop_path_rate: 0.0
+              hidden_act: gelu
+              hidden_dropout_prob: 0.0
+              hidden_size: 1024
+              image_size: 518
+              initializer_range: 0.02
+              layer_norm_eps: 1.e-6
+              layerscale_value: 1.0
+              mlp_ratio: 4
+              model_type: dinov2
+              num_attention_heads: 16
+              num_channels: 3
+              num_hidden_layers: 24
+              patch_size: 14
+              qkv_bias: true
+              torch_dtype: float32
+              use_swiglu_ffn: false
+            image_size: 518
+            use_cls_token: true
+
+scheduler:
+  target: hy3dshape.schedulers.FlowMatchEulerDiscreteScheduler
+  params:
+    num_train_timesteps: 1000
+
+image_processor:
+  target: hy3dshape.preprocessors.ImageProcessorV2
+  params:
+    size: 512
+    border_ratio: 0.15
+
+pipeline:
+  target: hy3dshape.pipelines.Hunyuan3DDiTFlowMatchingPipeline
@@ -0,0 +1,20 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}
@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "vision_encoder",
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 32,
+  "patch_size": 14,
+  "projection_dim": 1024,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.0"
+}
@@ -0,0 +1,37 @@
+{
+  "_class_name": "HunyuanPaintPipeline",
+  "_diffusers_version": "0.24.0",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "requires_safety_checker": false,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "modules",
+    "UNet2p5DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ],
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ]
+}
@@ -0,0 +1,15 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.23.1",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "set_alpha_to_one": true,
+  "steps_offset": 1,
+  "trained_betas": null,
+  "timestep_spacing": "trailing",
+  "rescale_betas_zero_snr": true
+}
@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "stabilityai/stable-diffusion-2",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.0.dev0",
+  "vocab_size": 49408
+}
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "name_or_path": "stabilityai/stable-diffusion-2",
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
@@ -0,0 +1,45 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.10.0.dev0",
+  "act_fn": "silu",
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "cross_attention_dim": 1024,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "sample_size": 64,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "use_linear_projection": true
+}
@@ -0,0 +1,29 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.10.0.dev0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 768,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}
@@ -0,0 +1,19 @@
+target: hy3dshape.models.ShapeVAE
+params:
+  num_latents: 4096
+  embed_dim: 64
+  num_freqs: 8
+  include_pi: false
+  heads: 16
+  width: 1024
+  num_encoder_layers: 8
+  num_decoder_layers: 16
+  qkv_bias: false
+  qk_norm: true
+  scale_factor: 1.0039506158752403
+  geo_decoder_mlp_expand_ratio: 4
+  geo_decoder_downsample_ratio: 1
+  geo_decoder_ln_post: true
+  point_feats: 4
+  pc_size: 81920
+  pc_sharpedge_size: 0