Duplicate from YiYiXu/shap-e-img2img

Co-authored-by: YiYi Xu <YiYiXu@users.noreply.huggingface.co>

.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 +1,3 @@
+---
+duplicated_from: YiYiXu/shap-e-img2img
+---

image_encoder/config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "openai/clip-vit-large-patch14",
+  "architectures": [
+    "CLIPVisionModel"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 1024,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "patch_size": 14,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2"
+}

image_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49767fbe1b9ea4688056a86db9404053b9a34c3f6a95776cb85622e7ea8a35ae
+size 1212850925

image_processor/preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "ShapEPriorPipeline",
+  "_diffusers_version": "0.17.0.dev0",
+  "scheduler": [
+    "diffusers",
+    "HeunDiscreteScheduler"
+  ],
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModel"
+  ],
+  "image_processor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "prior": [
+    "diffusers",
+    "PriorTransformer"
+  ],
+  "renderer": [
+    "shap_e",
+    "ShapERenderer"
+  ]
+}

prior/config.json

@@ -0,0 +1,19 @@
+{
+  "_class_name": "PriorTransformer",
+  "_diffusers_version": "0.18.0.dev0",
+  "added_emb_type": null,
+  "additional_embeddings": 0,
+  "attention_head_dim": 128,
+  "clip_embed_dim": 2048,
+  "dropout": 0.0,
+  "embedding_dim": 1024,
+  "embedding_proj_dim": 1024,
+  "embedding_proj_norm_type": "layer",
+  "encoder_hid_proj_type": null,
+  "norm_in_type": "layer",
+  "num_attention_heads": 8,
+  "num_embeddings": 1024,
+  "num_layers": 24,
+  "time_embed_act_fn": "gelu",
+  "time_embed_dim": 4096
+}

prior/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d293731644d9c6de6e7bd22bb1db5a52cb7b0f35ca452cbdbb8cf1bc727316e
+size 1263994731

renderer/config.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "ShapERenderer",
+  "_diffusers_version": "0.18.0.dev0",
+  "act_fn": "swish",
+  "d_hidden": 256,
+  "d_latent": 1024,
+  "insert_direction_at": 4,
+  "n_hidden_layers": 6,
+  "n_output": 12,
+  "param_names": [
+    "nerstf.mlp.0.weight",
+    "nerstf.mlp.1.weight",
+    "nerstf.mlp.2.weight",
+    "nerstf.mlp.3.weight"
+  ],
+  "param_shapes": [
+    [
+      256,
+      93
+    ],
+    [
+      256,
+      256
+    ],
+    [
+      256,
+      256
+    ],
+    [
+      256,
+      256
+    ]
+  ]
+}

renderer/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b50111f786c3dfca1d14cb1536a761cbc6826923a1f0021a19e156df5e171ee
+size 905200536

scheduler/scheduler_config.json

@@ -0,0 +1,11 @@
+{
+  "_class_name": "HeunDiscreteScheduler",
+  "_diffusers_version": "0.17.0.dev0",
+  "beta_schedule": "exp",
+  "trained_betas": null,
+  "num_train_timesteps": 1024,
+  "clip_sample": true,
+  "clip_sample_range": 1.0,
+  "prediction_type": "sample",
+  "use_karras_sigmas": true,
+}