End of training

README.md

@@ -1,7 +1,7 @@
 
 ---
 license: creativeml-openrail-m
-base_model: stabilityai/stable-diffusion-xl-base-1.0
+base_model: camapblue/bellagio-ai-t2i-ben-thanh-market
 dataset: bellagio-ai/t2i-one-pillar-pagoda
 tags:
 - stable-diffusion-xl
@@ -13,7 +13,7 @@ inference: true
     
 # Text-to-image finetuning - camapblue/bellagio-ai-t2i-vietnam-pictures-concat
 
-This pipeline was finetuned from **stabilityai/stable-diffusion-xl-base-1.0** on the **bellagio-ai/t2i-one-pillar-pagoda** dataset. Below are some example images generated with the finetuned pipeline using the following prompt: photography of One Pillar pagoda Ha Noi city Vietnam: 
+This pipeline was finetuned from **camapblue/bellagio-ai-t2i-ben-thanh-market** on the **bellagio-ai/t2i-one-pillar-pagoda** dataset. Below are some example images generated with the finetuned pipeline using the following prompt: photography of front of One Pillar pagoda Ha Noi city Vietnam: 
 
 ![img_0](./image_0.png)
 ![img_1](./image_1.png)

checkpoint-1000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b5276eef30916caef6a6b1ddf307e4ce1c4b310ab898cf95bbd9e1498a1585a
+size 5151956387

checkpoint-1000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:058ed24b116f1244e0fd117958637ecd73e796fdc904c4b2071c36f4b1ee6b18
+size 14727

checkpoint-1000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68cff80b680ddf6e7abbef98b5f336b97f9b5963e2209307f639383870e8cc71
+size 557

checkpoint-1000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:786fda73ee6e7361a6d5b31f3abf78d09766236828db931d4ee9c615b06ffa13
+size 563

checkpoint-1000/unet/config.json

@@ -0,0 +1,72 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.21.4",
+  "_name_or_path": "camapblue/bellagio-ai-t2i-ben-thanh-market",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "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": 4,
+  "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": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 128,
+  "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,
+    2,
+    10
+  ],
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

checkpoint-1000/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f4c442f6af33a7477e1c8d8fa1dffb1b40c236cb0de1230087fcf18e43a5cc
+size 10270077736

checkpoint-500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739a76e5e4a5838ca83715228523caa6270a77ae01c0d341cc9c8f0a95a21e5d
+size 5151956387

checkpoint-500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d8cc2d8aafc6eb28919c1ac4f8078edd82ccb394a07c391b78336633b3df7a
+size 14663

checkpoint-500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f196a54202bb4ba1220e8c59f42f9cda0702d68ea83147d814c2fb2f36b8f2
+size 557

checkpoint-500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a4d4182d95f023de43163930d7bbb32e380b0edfee3a7603157312ae7b79dc2
+size 563

checkpoint-500/unet/config.json

@@ -0,0 +1,72 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.21.4",
+  "_name_or_path": "camapblue/bellagio-ai-t2i-ben-thanh-market",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "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": 4,
+  "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": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 128,
+  "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,
+    2,
+    10
+  ],
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

checkpoint-500/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32e31842c6a2590cafedaa27f92655fb2db0e56a9384c2382eaa153d259c8be7
+size 10270077736

model_index.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "StableDiffusionXLPipeline",
   "_diffusers_version": "0.21.4",
-  "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
+  "_name_or_path": "camapblue/bellagio-ai-t2i-ben-thanh-market",
   "force_zeros_for_empty_prompt": true,
   "scheduler": [
     "diffusers",

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/76d28af79639c28a79fa5c6c6468febd3490a37e/text_encoder",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--camapblue--bellagio-ai-t2i-ben-thanh-market/snapshots/4774b9652e1ca93fc2aa0abbf3b1b4dffbe688de/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],

text_encoder_2/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/76d28af79639c28a79fa5c6c6468febd3490a37e/text_encoder_2",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--camapblue--bellagio-ai-t2i-ben-thanh-market/snapshots/4774b9652e1ca93fc2aa0abbf3b1b4dffbe688de/text_encoder_2",
   "architectures": [
     "CLIPTextModelWithProjection"
   ],

tokenizer/special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer/tokenizer_config.json

@@ -18,6 +18,7 @@
       "special": true
     }
   },
+  "additional_special_tokens": [],
   "bos_token": "<|startoftext|>",
   "clean_up_tokenization_spaces": true,
   "do_lower_case": true,

tokenizer_2/special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "!",
+  "pad_token": {
+    "content": "!",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer_2/tokenizer_config.json

@@ -26,6 +26,7 @@
       "special": true
     }
   },
+  "additional_special_tokens": [],
   "bos_token": "<|startoftext|>",
   "clean_up_tokenization_spaces": true,
   "do_lower_case": true,

unet/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.21.4",
-  "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
+  "_name_or_path": "camapblue/bellagio-ai-t2i-ben-thanh-market",
   "act_fn": "silu",
   "addition_embed_type": "text_time",
   "addition_embed_type_num_heads": 64,

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49de16b3d763cb2d2a567be2a6845f3c8e351f25a8bd5eae59c8c7ab891feb1b
+oid sha256:29f4c442f6af33a7477e1c8d8fa1dffb1b40c236cb0de1230087fcf18e43a5cc
 size 10270077736