Upload 6 files

README.md

@@ -1,3 +1,16 @@
----
-license: mit
----
+---
+library_name: trellis
+pipeline_tag: text-to-3d
+license: mit
+language:
+- en
+---
+# TRELLIS Text Base
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+The text conditioned version of TRELLIS with model size B, 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_flow_txt_dit_B_64l8p2_fp16.json

@@ -0,0 +1,19 @@
+{
+    "name": "SLatFlowModel",
+    "args": {
+        "resolution": 64,
+        "in_channels": 8,
+        "out_channels": 8,
+        "model_channels": 768,
+        "cond_channels": 768,
+        "num_blocks": 12,
+        "num_heads": 12,
+        "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/slat_flow_txt_dit_B_64l8p2_fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36312c77a150947041638c0a1eb382be73d5381e086ea0bfa2ba9525af4408ad
+size 372419896

ckpts/ss_flow_txt_dit_B_16l8_fp16.json

@@ -0,0 +1,17 @@
+{
+    "name": "SparseStructureFlowModel",
+    "args": {
+        "resolution": 16,
+        "in_channels": 8,
+        "out_channels": 8,
+        "model_channels": 768,
+        "cond_channels": 768,
+        "num_blocks": 12,
+        "num_heads": 12,
+        "mlp_ratio": 4,
+        "patch_size": 1,
+        "pe_mode": "ape",
+        "qk_rms_norm": true,
+        "use_fp16": true
+    }
+}

ckpts/ss_flow_txt_dit_B_16l8_fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9fa7a2c5deae18307ebfcb29c955b11130e4eb1a88de05c384104c493dee3ff
+size 327736456

pipeline.json

@@ -0,0 +1,60 @@
+{
+    "name": "TrellisTextTo3DPipeline",
+    "args": {
+        "models": {
+            "sparse_structure_decoder": "JeffreyXiang/TRELLIS-image-large/ckpts/ss_dec_conv3d_16l8_fp16",
+            "sparse_structure_flow_model": "ckpts/ss_flow_txt_dit_B_16l8_fp16",
+            "slat_decoder_gs": "JeffreyXiang/TRELLIS-image-large/ckpts/slat_dec_gs_swin8_B_64l8gs32_fp16",
+            "slat_decoder_rf": "JeffreyXiang/TRELLIS-image-large/ckpts/slat_dec_rf_swin8_B_64l8r16_fp16",
+            "slat_decoder_mesh": "JeffreyXiang/TRELLIS-image-large/ckpts/slat_dec_mesh_swin8_B_64l8m256c_fp16",
+            "slat_flow_model": "ckpts/slat_flow_txt_dit_B_64l8p2_fp16"
+        },
+        "sparse_structure_sampler": {
+            "name": "FlowEulerGuidanceIntervalSampler",
+            "args": {
+                "sigma_min": 1e-5
+            },
+            "params": {
+                "steps": 25,
+                "cfg_strength": 7.5,
+                "cfg_interval": [0.5, 0.95],
+                "rescale_t": 3.0
+            }
+        },
+        "slat_sampler": {
+            "name": "FlowEulerGuidanceIntervalSampler",
+            "args": {
+                "sigma_min": 1e-5
+            },
+            "params": {
+                "steps": 25,
+                "cfg_strength": 7.5,
+                "cfg_interval": [0.5, 0.95],
+                "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
+            ]
+        },
+        "text_cond_model": "openai/clip-vit-large-patch14"
+    }
+}