Upload 11 files

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,16 @@
 ---
+library_name: trellis
+pipeline_tag: image-to-3d
 license: mit
+language:
+- en
 ---
+# TRELLIS Image Large
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+The image conditioned version of TRELLIS, a large 3D genetive model. It was introduced in the paper [Structured 3D Latents for Scalable and Versatile 3D Generation](https://huggingface.co/papers/2412.01506).
+
+Project page: https://trellis3d.github.io/
+
+Code: https://github.com/Microsoft/TRELLIS

ckpts/slat_dec_gs_swin8_B_64l8gs32_fp16.json

@@ -0,0 +1,31 @@
+{
+    "name": "SLatGaussianDecoder",
+    "args": {
+        "resolution": 64,
+        "model_channels": 768,
+        "latent_channels": 8,
+        "num_blocks": 12,
+        "num_heads": 12,
+        "mlp_ratio": 4,
+        "attn_mode": "swin",
+        "window_size": 8,
+        "use_fp16": true,
+        "representation_config": {
+            "lr": {
+                "_xyz": 1.0,
+                "_features_dc": 1.0,
+                "_opacity": 1.0,
+                "_scaling": 1.0,
+                "_rotation": 0.1
+            },
+            "perturb_offset": true,
+            "voxel_size": 1.5,
+            "num_gaussians": 32,
+            "2d_filter_kernel_size": 0.1,
+            "3d_filter_kernel_size": 9e-4,
+            "scaling_bias": 4e-3,
+            "opacity_bias": 0.1,
+            "scaling_activation": "softplus"
+        }
+    }
+}

ckpts/slat_dec_mesh_swin8_B_64l8m256c_fp16.json

@@ -0,0 +1,17 @@
+{
+    "name": "SLatMeshDecoder",
+    "args": {
+        "resolution": 64,
+        "model_channels": 768,
+        "latent_channels": 8,
+        "num_blocks": 12,
+        "num_heads": 12,
+        "mlp_ratio": 4,
+        "attn_mode": "swin",
+        "window_size": 8,
+        "use_fp16": true,
+        "representation_config": {
+            "use_color": true
+        }
+    }
+}

ckpts/slat_dec_rf_swin8_B_64l8r16_fp16.json

@@ -0,0 +1,18 @@
+{
+    "name": "SLatRadianceFieldDecoder",
+    "args": {
+        "resolution": 64,
+        "model_channels": 768,
+        "latent_channels": 8,
+        "num_blocks": 12,
+        "num_heads": 12,
+        "mlp_ratio": 4,
+        "attn_mode": "swin",
+        "window_size": 8,
+        "use_fp16": true,
+        "representation_config": {
+            "rank": 16,
+            "dim": 8
+        }
+    }
+}

ckpts/slat_enc_swin8_B_64l8_fp16.json

@@ -0,0 +1,15 @@
+{
+    "name": "SLatEncoder",
+    "args": {
+        "resolution": 64,
+        "in_channels": 1024,
+        "model_channels": 768,
+        "latent_channels": 8,
+        "num_blocks": 12,
+        "num_heads": 12,
+        "mlp_ratio": 4,
+        "attn_mode": "swin",
+        "window_size": 8,
+        "use_fp16": true
+    }
+}

ckpts/slat_flow_img_dit_L_64l8p2_fp16.json

@@ -0,0 +1,19 @@
+{
+    "name": "SLatFlowModel",
+    "args": {
+        "resolution": 64,
+        "in_channels": 8,
+        "out_channels": 8,
+        "model_channels": 1024,
+        "cond_channels": 1024,
+        "num_blocks": 24,
+        "num_heads": 16,
+        "mlp_ratio": 4,
+        "patch_size": 2,
+        "num_io_res_blocks": 2,
+        "io_block_channels": [128],
+        "pe_mode": "ape",
+        "qk_rms_norm": true,
+        "use_fp16": true
+    }
+}

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_enc_conv3d_16l8_fp16.json

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

ckpts/ss_flow_img_dit_L_16l8_fp16.json

@@ -0,0 +1,17 @@
+{
+    "name": "SparseStructureFlowModel",
+    "args": {
+        "resolution": 16,
+        "in_channels": 8,
+        "out_channels": 8,
+        "model_channels": 1024,
+        "cond_channels": 1024,
+        "num_blocks": 24,
+        "num_heads": 16,
+        "mlp_ratio": 4,
+        "patch_size": 1,
+        "pe_mode": "ape",
+        "qk_rms_norm": true,
+        "use_fp16": true
+    }
+}

pipeline.json

@@ -0,0 +1,60 @@
+{
+    "name": "TrellisImageTo3DPipeline",
+    "args": {
+        "models": {
+            "sparse_structure_decoder": "ckpts/ss_dec_conv3d_16l8_fp16",
+            "sparse_structure_flow_model": "ckpts/ss_flow_img_dit_L_16l8_fp16",
+            "slat_decoder_gs": "ckpts/slat_dec_gs_swin8_B_64l8gs32_fp16",
+            "slat_decoder_rf": "ckpts/slat_dec_rf_swin8_B_64l8r16_fp16",
+            "slat_decoder_mesh": "ckpts/slat_dec_mesh_swin8_B_64l8m256c_fp16",
+            "slat_flow_model": "ckpts/slat_flow_img_dit_L_64l8p2_fp16"
+        },
+        "sparse_structure_sampler": {
+            "name": "FlowEulerGuidanceIntervalSampler",
+            "args": {
+                "sigma_min": 1e-5
+            },
+            "params": {
+                "steps": 25,
+                "cfg_strength": 5.0,
+                "cfg_interval": [0.5, 1.0],
+                "rescale_t": 3.0
+            }
+        },
+        "slat_sampler": {
+            "name": "FlowEulerGuidanceIntervalSampler",
+            "args": {
+                "sigma_min": 1e-5
+            },
+            "params": {
+                "steps": 25,
+                "cfg_strength": 5.0,
+                "cfg_interval": [0.5, 1.0],
+                "rescale_t": 3.0
+            }
+        },
+        "slat_normalization": {
+            "mean": [
+                -2.1687545776367188,
+                -0.004347046371549368,
+                -0.13352349400520325,
+                -0.08418072760105133,
+                -0.5271206498146057,
+                0.7238689064979553,
+                -1.1414450407028198,
+                1.2039363384246826
+            ],
+            "std": [
+                2.377650737762451,
+                2.386378288269043,
+                2.124418020248413,
+                2.1748552322387695,
+                2.663944721221924,
+                2.371192216873169,
+                2.6217446327209473,
+                2.684523105621338
+            ]
+        },
+        "image_cond_model": "dinov2_vitl14_reg"
+    }
+}