Upload model weights

model_index.json

@@ -0,0 +1,52 @@
+{
+  "_class_name": "TrellisText2SLatPipeline",
+  "_diffusers_version": "0.35.1",
+  "scheduler": [
+    "genlab.schedulers.scheduling_flow_match_euler_discrete",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizerFast"
+  ],
+  "transformer": [
+    "genlab.models.diffusers_modules.trellis.transformer_trellis_slat",
+    "TrellisSLatDiTModel"
+  ],
+  "vae_decoder_gs": [
+    "genlab.models.diffusers_modules.trellis.autoencoder_kl_trellis_slat",
+    "SLatGaussianDecoder"
+  ],
+  "vae_decoder_mesh": [
+    "genlab.models.diffusers_modules.trellis.autoencoder_kl_trellis_slat",
+    "SLatMeshDecoder"
+  ],
+  "vae_encoder": [
+    "genlab.models.diffusers_modules.trellis.autoencoder_kl_trellis_slat",
+    "SLatEncoder"
+  ],
+  "vae_mean_value": [
+    -2.1687545776367188,
+    -0.004347046371549368,
+    -0.13352349400520325,
+    -0.08418072760105133,
+    -0.5271206498146057,
+    0.7238689064979553,
+    -1.1414450407028198,
+    1.2039363384246826
+  ],
+  "vae_std_value": [
+    2.377650737762451,
+    2.386378288269043,
+    2.124418020248413,
+    2.1748552322387695,
+    2.663944721221924,
+    2.371192216873169,
+    2.6217446327209473,
+    2.684523105621338
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,19 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.35.1",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_dt": false,
+  "invert_sigmas": false,
+  "max_image_seq_len": 4096,
+  "max_shift": 1.15,
+  "num_train_timesteps": 1000,
+  "shift": 1.0,
+  "shift_terminal": null,
+  "stochastic_sampling": false,
+  "time_shift_type": "exponential",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": false,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "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": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778d02eb9e707c3fbaae0b67b79ea0d1399b52e624fb634f2f19375ae7c047c3
+size 492265168

tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

transformer/config.json

@@ -0,0 +1,21 @@
+{
+  "_class_name": "TrellisSLatDiTModel",
+  "_diffusers_version": "0.35.1",
+  "block_out_channels": [
+    256
+  ],
+  "cross_attention_dim": 768,
+  "in_channels": 8,
+  "inner_dim": 1280,
+  "mlp_ratio": 4.0,
+  "num_attention_heads": 16,
+  "num_layers": 28,
+  "out_channels": 8,
+  "patch_size": 2,
+  "qk_norm_cross": null,
+  "qk_norm_self": "rms_norm",
+  "resnet_num_blocks": 3,
+  "resnet_scale_factor": 2,
+  "resnet_skip_connection": true,
+  "resolution": 64
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89fd5920c2ea2205d9aa46b03287bab36f877328393740e7925695a68b27c4c7
+size 4293737736

vae_decoder_gs/config.json

@@ -0,0 +1,28 @@
+{
+  "_class_name": "SLatGaussianDecoder",
+  "_diffusers_version": "0.35.1",
+  "dim": 768,
+  "latent_channels": 8,
+  "mlp_ratio": 4.0,
+  "num_attention_heads": 12,
+  "num_layers": 12,
+  "qk_norm": null,
+  "representation_config": {
+    "2d_filter_kernel_size": 0.1,
+    "3d_filter_kernel_size": 0.0009,
+    "lr": {
+      "_features_dc": 1.0,
+      "_opacity": 1.0,
+      "_rotation": 0.1,
+      "_scaling": 1.0,
+      "_xyz": 1.0
+    },
+    "num_gaussians": 32,
+    "opacity_bias": 0.1,
+    "perturb_offset": true,
+    "scaling_activation": "softplus",
+    "scaling_bias": 0.004,
+    "voxel_size": 1.5
+  },
+  "resolution": 64
+}

vae_decoder_gs/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:357c322a76d8f23d31121fc8856420f373dd0a886feb84dde4795ef70fc4b480
+size 341490976

vae_decoder_mesh/config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "SLatMeshDecoder",
+  "_diffusers_version": "0.35.1",
+  "dim": 768,
+  "latent_channels": 8,
+  "mlp_ratio": 4.0,
+  "num_attention_heads": 12,
+  "num_layers": 12,
+  "qk_norm": null,
+  "representation_config": {
+    "use_color": true
+  },
+  "resolution": 64
+}

vae_decoder_mesh/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93f2271529d8027f410b45077f7d5d99a0cb34bed9d10d1bfbdc04499d944843
+size 363723420

vae_encoder/config.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "SLatEncoder",
+  "_diffusers_version": "0.35.1",
+  "dim": 768,
+  "in_channels": 1024,
+  "latent_channels": 8,
+  "mlp_ratio": 4.0,
+  "num_attention_heads": 12,
+  "num_layers": 12,
+  "qk_norm": null,
+  "resolution": 64
+}

vae_encoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59955154dceb0f10cb0c4935d1cb6e9a6b4d024a214b0251f09e4b5899b07278
+size 343282824