End of training

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 val_imgs_grid.png filter=lfs diff=lfs merge=lfs -text
+.ipynb_checkpoints/val_imgs_grid-checkpoint.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -9,6 +9,11 @@ tags:
 - text-to-image
 - diffusers
 - diffusers-training
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- diffusers
+- diffusers-training
 ---
 
 <!-- This model card has been generated automatically according to the information the training script had access to. You

checkpoint-5000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23cdc2729fe81e52801e3be2665169ec3eee5ac9a2f35c31a4e0b114c28b9cee
+size 6876750164

checkpoint-5000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9cac80265102cd7cd6bd2fdfd27876f8ec54ebf9e72874f7e2a8cfea992bdc7
+size 14472

checkpoint-5000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41216328ab75de937007afb04d76156949bedb908461001a451c8991c2ba8cca
+size 988

checkpoint-5000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e7b2fc9d31c1b2690936f6ca28d591b67b8d63ea4775446def6c053d47c932d
+size 1000

checkpoint-5000/unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.33.0.dev0",
+  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "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": 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": 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": 64,
+  "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": false
+}

checkpoint-5000/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def1cf70cc49bd5f2ac98f1e25ee83dd3a6b9e635af4d19df38a7b4d34cacedc
+size 3438167536

checkpoint-5000/unet_ema/config.json

@@ -0,0 +1,75 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.33.0.dev0",
+  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "decay": 0.9999,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "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": 4,
+  "inv_gamma": 1.0,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "min_decay": 0.0,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "optimization_step": 5000,
+  "out_channels": 4,
+  "power": 0.6666666666666666,
+  "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": 64,
+  "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,
+  "update_after_step": 0,
+  "use_ema_warmup": false,
+  "use_linear_projection": false
+}

checkpoint-5000/unet_ema/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6f87c172172d8cce603a6eb85fac73dc14918be746b027a555b0390dfe2531a
+size 3438167536

model_index.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "StableDiffusionPipeline",
   "_diffusers_version": "0.33.0.dev0",
-  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
   "feature_extractor": [
     "transformers",
     "CLIPImageProcessor"

safety_checker/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/safety_checker",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--stable-diffusion-v1-5--stable-diffusion-v1-5/snapshots/451f4fe16113bff5a5d2269ed5ad43b0592e9a14/safety_checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
   ],

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -18,7 +18,7 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 1,
-  "projection_dim": 512,
+  "projection_dim": 768,
   "torch_dtype": "float16",
   "transformers_version": "4.48.1",
   "vocab_size": 49408

unet/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.33.0.dev0",
-  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
   "act_fn": "silu",
   "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ffe0ed25670a79299e4e43969939e64e0617335c84efe03f6162c761f6c0016
+oid sha256:a6f87c172172d8cce603a6eb85fac73dc14918be746b027a555b0390dfe2531a
 size 3438167536

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.33.0.dev0",
-  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
   "act_fn": "silu",
   "block_out_channels": [
     128,