[ADD] fp16 checkpoint

model_index.json

@@ -1,24 +1,25 @@
 {
-    "_class_name":"MarigoldPipeline",
-    "_diffusers_version":"0.24.0",
-    "unet":[
-       "diffusers",
-       "UNet2DConditionModel"
-    ],
-    "vae":[
-       "diffusers",
-       "AutoencoderKL"
-    ],
-    "scheduler":[
-       "diffusers",
-       "DDIMScheduler"
-    ],
-    "text_encoder":[
-       "transformers",
-       "CLIPTextModel"
-    ],
-    "tokenizer":[
-       "transformers",
-       "CLIPTokenizer"
-    ]
- }
+  "_class_name": "MarigoldPipeline",
+  "_diffusers_version": "0.26.2",
+  "_name_or_path": "checkpoint/Marigold",
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -1,14 +1,20 @@
 {
   "_class_name": "DDIMScheduler",
-  "_diffusers_version": "0.8.0",
+  "_diffusers_version": "0.26.2",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
   "num_train_timesteps": 1000,
   "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
   "set_alpha_to_one": false,
   "skip_prk_steps": true,
   "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "leading",
   "trained_betas": null
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "hf-models/stable-diffusion-v2-768x768/text_encoder",
+  "_name_or_path": "checkpoint/Marigold/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -19,7 +19,7 @@
   "num_hidden_layers": 23,
   "pad_token_id": 1,
   "projection_dim": 512,
-  "torch_dtype": "float32",
-  "transformers_version": "4.25.0.dev0",
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
   "vocab_size": 49408
 }

text_encoder/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1827c465450322616f06dea41596eac7d493f4e95904dcb51f0fc745c4e13f
+size 680820392

text_encoder/pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc767ee894a2d26166aa7c22b7b297a1ff8e246493734490dd048087d4c9c07
+size 680899947

tokenizer/tokenizer_config.json

@@ -1,34 +1,38 @@
 {
   "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|startoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
   "do_lower_case": true,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "<|endoftext|>",
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "hf-models/stable-diffusion-v2-768x768/tokenizer",
-  "pad_token": "<|endoftext|>",
-  "special_tokens_map_file": "./special_tokens_map.json",
+  "pad_token": "!",
   "tokenizer_class": "CLIPTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<|endoftext|>"
 }

unet/config.json

@@ -1,14 +1,18 @@
 {
   "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.20.1",
-  "_name_or_path": "Bingxin/Marigold/unet",
+  "_diffusers_version": "0.26.2",
+  "_name_or_path": "checkpoint/Marigold/unet",
   "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
   "attention_head_dim": [
     5,
     10,
     20,
     20
   ],
+  "attention_type": "default",
   "block_out_channels": [
     320,
     640,
@@ -16,7 +20,12 @@
     1280
   ],
   "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
   "cross_attention_dim": 1024,
+  "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
     "CrossAttnDownBlock2D",
@@ -24,21 +33,41 @@
     "DownBlock2D"
   ],
   "downsample_padding": 1,
+  "dropout": 0.0,
   "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
   "flip_sin_to_cos": true,
   "freq_shift": 0,
   "in_channels": 8,
   "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
   "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
   "norm_eps": 1e-05,
   "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
   "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
   "sample_size": 96,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
   "up_block_types": [
     "UpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
+  "upcast_attention": false,
   "use_linear_projection": true
-}
+}

unet/diffusion_pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:794aca23894df15815c39312aaaa8e1243d6ab98e64d1cd6fdb703bd68878e90
+size 1732130133

unet/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da9c13e214461c2cf82e4a0f125d914976522e53806a54d508e30ea5b8cd67f2
+size 1731927776

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.8.0",
-  "_name_or_path": "hf-models/stable-diffusion-v2-768x768/vae",
+  "_diffusers_version": "0.26.2",
+  "_name_or_path": "checkpoint/Marigold/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -15,12 +15,14 @@
     "DownEncoderBlock2D",
     "DownEncoderBlock2D"
   ],
+  "force_upcast": true,
   "in_channels": 3,
   "latent_channels": 4,
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
   "sample_size": 768,
+  "scaling_factor": 0.18215,
   "up_block_types": [
     "UpDecoderBlock2D",
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44915add42092106e70bffac475aae4283b5e8167a8a0c5f55ccc667ee4ebeb5
+size 167405651

vae/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
+size 167335342