Upload Pixal3D-T model weights and pipeline config

ckpts/shape_dec_next_dc_f16c32_fp16.json

@@ -0,0 +1,24 @@
+{
+    "name": "FlexiDualGridVaeDecoder",
+    "args": {
+        "resolution": 256,
+        "model_channels": [1024, 512, 256, 128, 64],
+        "latent_channels": 32,
+        "num_blocks": [4, 16, 8, 4, 0],
+        "block_type": [
+            "SparseConvNeXtBlock3d",
+            "SparseConvNeXtBlock3d",
+            "SparseConvNeXtBlock3d",
+            "SparseConvNeXtBlock3d",
+            "SparseConvNeXtBlock3d"
+        ],
+        "up_block_type": [
+            "SparseResBlockC2S3d",
+            "SparseResBlockC2S3d",
+            "SparseResBlockC2S3d",
+            "SparseResBlockC2S3d"
+        ],
+        "block_args": [{}, {}, {}, {}, {}],
+        "use_fp16": true
+    }
+}

ckpts/shape_dec_next_dc_f16c32_fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3b718d3e43e4f8780e9a24ac6fff231811a67e3b058e336e10fe654c911d581
+size 948490494

ckpts/slat_flow_img2shape_dit_1_3B_1024_bf16.json

@@ -0,0 +1,20 @@
+{
+    "name": "ElasticSLatFlowModel",
+    "args": {
+        "resolution": 64,
+        "in_channels": 32,
+        "out_channels": 32,
+        "model_channels": 1536,
+        "cond_channels": 1024,
+        "num_blocks": 30,
+        "num_heads": 12,
+        "mlp_ratio": 5.3334,
+        "pe_mode": "rope",
+        "share_mod": true,
+        "initialization": "scaled",
+        "qk_rms_norm": true,
+        "qk_rms_norm_cross": true,
+        "image_attn_mode": "proj",
+        "proj_in_channels": 2048
+    }
+}

ckpts/slat_flow_img2shape_dit_1_3B_1024_bf16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e6d1df0e62bc5bc863320d1d63d6b996235eef4abb8b851e878c88f316369f1
+size 5546764048

ckpts/slat_flow_img2shape_dit_1_3B_512_bf16.json

@@ -0,0 +1,20 @@
+{
+    "name": "ElasticSLatFlowModel",
+    "args": {
+        "resolution": 32,
+        "in_channels": 32,
+        "out_channels": 32,
+        "model_channels": 1536,
+        "cond_channels": 1024,
+        "num_blocks": 30,
+        "num_heads": 12,
+        "mlp_ratio": 5.3334,
+        "pe_mode": "rope",
+        "share_mod": true,
+        "initialization": "scaled",
+        "qk_rms_norm": true,
+        "qk_rms_norm_cross": true,
+        "image_attn_mode": "proj",
+        "proj_in_channels": 2048
+    }
+}

ckpts/slat_flow_img2shape_dit_1_3B_512_bf16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63569838c1da93f010e2fa805b202ecf802cc758830230abac202a81b70e5b45
+size 5546764048

ckpts/slat_flow_imgshape2tex_dit_1_3B_1024_bf16.json

@@ -0,0 +1,20 @@
+{
+    "name": "ElasticSLatFlowModel",
+    "args": {
+        "resolution": 64,
+        "in_channels": 64,
+        "out_channels": 32,
+        "model_channels": 1536,
+        "cond_channels": 1024,
+        "num_blocks": 30,
+        "num_heads": 12,
+        "mlp_ratio": 5.3334,
+        "pe_mode": "rope",
+        "share_mod": true,
+        "initialization": "scaled",
+        "qk_rms_norm": true,
+        "qk_rms_norm_cross": true,
+        "image_attn_mode": "proj",
+        "proj_in_channels": 2048
+    }
+}

ckpts/slat_flow_imgshape2tex_dit_1_3B_1024_bf16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65df179ad02f9e92bc18335d7861fadd95f268e6249217352468dd83cb79d1d0
+size 5546960656

ckpts/ss_dec_conv3d_16l8_fp16.json

@@ -0,0 +1,12 @@
+
+{
+    "name": "SparseStructureDecoder",
+    "args": {
+        "out_channels": 1,
+        "latent_channels": 8,
+        "num_res_blocks": 2,
+        "num_res_blocks_middle": 2,
+        "channels": [512, 128, 32],
+        "use_fp16": true
+    }
+}

ckpts/ss_dec_conv3d_16l8_fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c76d4a40519aa2d711cc263a8404105231ac26db31d946bed48b84fee79009a
+size 147591972

ckpts/ss_flow_img_dit_1_3B_64_bf16.json

@@ -0,0 +1,19 @@
+{
+    "name": "SparseStructureFlowModel",
+    "args": {
+        "resolution": 16,
+        "in_channels": 8,
+        "out_channels": 8,
+        "model_channels": 1536,
+        "cond_channels": 1024,
+        "num_blocks": 30,
+        "num_heads": 12,
+        "mlp_ratio": 5.3334,
+        "pe_mode": "rope",
+        "share_mod": true,
+        "initialization": "scaled",
+        "qk_rms_norm": true,
+        "qk_rms_norm_cross": true,
+        "image_attn_mode": "proj"
+    }
+}

ckpts/ss_flow_img_dit_1_3B_64_bf16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d0147bb347eb61fa81c304cc68c7fd69d447e91870357a549b47e1d0fd77242
+size 5359822584

ckpts/tex_dec_next_dc_f16c32_fp16.json

@@ -0,0 +1,25 @@
+{
+    "name": "SparseUnetVaeDecoder",
+    "args": {
+        "out_channels": 6,
+        "model_channels": [1024, 512, 256, 128, 64],
+        "latent_channels": 32,
+        "num_blocks": [4, 16, 8, 4, 0],
+        "block_type": [
+            "SparseConvNeXtBlock3d",
+            "SparseConvNeXtBlock3d",
+            "SparseConvNeXtBlock3d",
+            "SparseConvNeXtBlock3d",
+            "SparseConvNeXtBlock3d"
+        ],
+        "up_block_type": [
+            "SparseResBlockC2S3d",
+            "SparseResBlockC2S3d",
+            "SparseResBlockC2S3d",
+            "SparseResBlockC2S3d"
+        ],
+        "block_args": [{}, {}, {}, {}, {}],
+        "pred_subdiv": false,
+        "use_fp16": true
+    }
+}

ckpts/tex_dec_next_dc_f16c32_fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ea69addea2ecd9312910f5f548234665eef51c088386180b7cd5b258645e3c
+size 948458812

pipeline.json

@@ -0,0 +1,94 @@
+{
+    "name": "Trellis2ImageTo3DPipeline",
+    "args": {
+        "models": {
+            "sparse_structure_decoder": "ckpts/ss_dec_conv3d_16l8_fp16",
+            "sparse_structure_flow_model": "ckpts/ss_flow_img_dit_1_3B_64_bf16",
+            "shape_slat_decoder": "ckpts/shape_dec_next_dc_f16c32_fp16",
+            "shape_slat_flow_model_512": "ckpts/slat_flow_img2shape_dit_1_3B_512_bf16",
+            "shape_slat_flow_model_1024": "ckpts/slat_flow_img2shape_dit_1_3B_1024_bf16",
+            "tex_slat_decoder": "ckpts/tex_dec_next_dc_f16c32_fp16",
+            "tex_slat_flow_model_1024": "ckpts/slat_flow_imgshape2tex_dit_1_3B_1024_bf16"
+        },
+        "sparse_structure_sampler": {
+            "name": "FlowEulerGuidanceIntervalSampler",
+            "args": {
+                "sigma_min": 1e-5
+            },
+            "params": {
+                "steps": 12,
+                "guidance_strength": 7.5,
+                "guidance_rescale": 0.7,
+                "guidance_interval": [0.6, 1.0],
+                "rescale_t": 5.0
+            }
+        },
+        "shape_slat_sampler": {
+            "name": "FlowEulerGuidanceIntervalSampler",
+            "args": {
+                "sigma_min": 1e-5
+            },
+            "params": {
+                "steps": 12,
+                "guidance_strength": 7.5,
+                "guidance_rescale": 0.5,
+                "guidance_interval": [0.6, 1.0],
+                "rescale_t": 3.0
+            }
+        },
+        "shape_slat_normalization": {
+            "mean": [
+                0.781296, 0.018091, -0.495192, -0.558457, 1.060530, 0.093252, 1.518149, -0.933218,
+                -0.732996, 2.604095, -0.118341, -2.143904, 0.495076, -2.179512, -2.130751, -0.996944,
+                0.261421, -2.217463, 1.260067, -0.150213, 3.790713, 1.481266, -1.046058, -1.523667,
+                -0.059621, 2.220780, 1.621212, 0.877230, 0.567247, -3.175944, -3.186688, 1.578665
+            ],
+            "std": [
+                5.972266, 4.706852, 5.445010, 5.209927, 5.320220, 4.547237, 5.020802, 5.444004,
+                5.226681, 5.683095, 4.831436, 5.286469, 5.652043, 5.367606, 5.525084, 4.730578,
+                4.805265, 5.124013, 5.530808, 5.619001, 5.103930, 5.417670, 5.269677, 5.547194,
+                5.634698, 5.235274, 6.110351, 5.511298, 6.237273, 4.879207, 5.347008, 5.405691
+            ]
+        },
+        "tex_slat_sampler": {
+            "name": "FlowEulerGuidanceIntervalSampler",
+            "args": {
+                "sigma_min": 1e-5
+            },
+            "params": {
+                "steps": 12,
+                "guidance_strength": 1.0,
+                "guidance_rescale": 0.0,
+                "guidance_interval": [0.6, 0.9],
+                "rescale_t": 3.0
+            }
+        },
+        "tex_slat_normalization": {
+            "mean": [
+                3.501659, 2.212398, 2.226094, 0.251093, -0.026248, -0.687364, 0.439898, -0.928075,
+                0.029398, -0.339596, -0.869527, 1.038479, -0.972385, 0.126042, -1.129303, 0.455149,
+                -1.209521, 2.069067, 0.544735, 2.569128, -0.323407, 2.293000, -1.925608, -1.217717,
+                1.213905, 0.971588, -0.023631, 0.106750, 2.021786, 0.250524, -0.662387, -0.768862
+            ],
+            "std": [
+                2.665652, 2.743913, 2.765121, 2.595319, 3.037293, 2.291316, 2.144656, 2.911822,
+                2.969419, 2.501689, 2.154811, 3.163343, 2.621215, 2.381943, 3.186697, 3.021588,
+                2.295916, 3.234985, 3.233086, 2.260140, 2.874801, 2.810596, 3.292720, 2.674999,
+                2.680878, 2.372054, 2.451546, 2.353556, 2.995195, 2.379849, 2.786195, 2.775190
+            ]
+        },
+        "image_cond_model": {
+            "name": "DinoV3FeatureExtractor",
+            "args": {
+                "model_name": "facebook/dinov3-vitl16-pretrain-lvd1689m"
+            }
+        },
+        "rembg_model": {
+            "name": "BiRefNet",
+            "args": {
+                "model_name": "briaai/RMBG-2.0"
+            }
+        },
+        "default_pipeline_type": "1536_cascade"
+    }
+}