Initial DIRECT model release

.gitattributes

@@ -0,0 +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

README.md

@@ -0,0 +1,43 @@
+---
+base_model:
+- black-forest-labs/FLUX.1-Fill-dev
+- microsoft/TRELLIS-image-large
+tags:
+- object-insertion
+- image-to-image
+- 3d-aware
+- pose-controllable-generation
+pipeline_tag: image-to-image
+---
+
+# DIRECT
+
+This repository contains the model weights for **Direct 3D-Aware Object Insertion via Decomposed Visual Proxies**.
+
+DIRECT performs pose-controllable object insertion by decomposing the insertion condition into visual proxies, including a reference object image, a geometry proxy rendered from a reconstructed 3D object, and a scene context image.
+
+Project page: https://gong1130.github.io/DIRECT/
+
+Code: https://github.com/Gong1130/DIRECT
+
+## Usage
+
+Please refer to the official code repository for installation instructions and **interactive demo** usage.
+
+## Model Details
+
+This repository contains **DIRECT-specific** weights **only**:
+
+- `lora.safetensors`
+- `condition_embedder.safetensors`
+- `x_embedder.safetensors`
+- `time_text_embed.safetensors`
+- `pooled_image_projector.safetensors`
+- `image_projector.safetensors`
+- `config.json`
+
+The model requires the following **external** models:
+
+- `black-forest-labs/FLUX.1-Fill-dev`
+- `google/siglip2-so400m-patch14-384`
+- `microsoft/TRELLIS-image-large`

condition_embedder.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:955a10ab50142b229ad9cc6ef807bac9c7bee6c8ef3b6fc0a14edc7400e34a77
+size 798872

config.json

@@ -0,0 +1,38 @@
+{
+  "model_type": "direct_pipeline",
+  "flux_model": "black-forest-labs/FLUX.1-Fill-dev",
+  "siglip_model": "google/siglip2-so400m-patch14-384",
+  "torch_dtype": "bfloat16",
+  "lora": {
+    "ranks": [128, 128],
+    "alphas": [128, 128],
+    "weights": [1, 1],
+    "n_loras": 2,
+    "double_blocks": 19,
+    "single_blocks": 38,
+    "text": {
+      "rank": 128,
+      "alpha": 128,
+      "token_length": 729
+    }
+  },
+  "condition_embedder": {
+    "input_dim": 64
+  },
+  "pooled_image_projector": {
+    "input_dim": 1152,
+    "output_dim": 768
+  },
+  "image_projector": {
+    "input_dim": 1152,
+    "output_dim": 4096
+  },
+  "weight_files": {
+    "lora": "lora.safetensors",
+    "condition_embedder": "condition_embedder.safetensors",
+    "x_embedder": "x_embedder.safetensors",
+    "time_text_embed": "time_text_embed.safetensors",
+    "pooled_image_projector": "pooled_image_projector.safetensors",
+    "image_projector": "image_projector.safetensors"
+  }
+}

image_projector.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a083dd6d0a6cca808b92c9933046400d203f9492943504215ce7f25dad85e6d4
+size 18890904

lora.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a1cb8165f291acd0850bbdd0c7e7694051921a22b993d059a180f1dce4876b
+size 896689296

pooled_image_projector.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71c61c3f4990a02150ac3109ef5f86949ae32272e2e2b68eb24fe747984c481e
+size 3542160

time_text_embed.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eab6be9862c33ef88fb131d9538f79468e871dd49bf86d99cba58ca6ebc2223a
+size 64525712

x_embedder.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7720552159ecc53f14a40792184e0c5b4bc02b0d829a13b3661ddb3d1c5aa90
+size 2365616