End of training

checkpoint-600/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5064bf2e7dff1a2bdfe4f52eeab3fbb386fcb6c0003d6f4ae53b49023ba1bb3
+size 1748632634

checkpoint-600/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67453d92e86eff90aa33d272e0e326981ca44be907d6ad468456fd7792991280
+size 14604

checkpoint-600/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e32b8db4f4cba2b7b0157ab60a064591c3802a9067529d5fddbb1c6c1e99660b
+size 988

checkpoint-600/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0f36e41e2134a0cb8e057035bef3a0e7ceb2166315b0342f0d0533146a770bb
+size 1000

checkpoint-600/unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.31.0.dev0",
+  "_name_or_path": "timbrooks/instruct-pix2pix",
+  "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": 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": 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-600/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27bc8b39d94ba73192b4ae2702783cb779ac9516d2489ea01744c8eb6648fd4e
+size 3438213624

model_index.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "StableDiffusionInstructPix2PixPipeline",
   "_diffusers_version": "0.31.0.dev0",
-  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "_name_or_path": "timbrooks/instruct-pix2pix",
   "feature_extractor": [
     "transformers",
     "CLIPImageProcessor"
@@ -10,14 +10,14 @@
     null,
     null
   ],
-  "requires_safety_checker": true,
+  "requires_safety_checker": false,
   "safety_checker": [
     "stable_diffusion",
     "StableDiffusionSafetyChecker"
   ],
   "scheduler": [
     "diffusers",
-    "PNDMScheduler"
+    "EulerAncestralDiscreteScheduler"
   ],
   "text_encoder": [
     "transformers",

safety_checker/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/autodl-tmp/hub/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/safety_checker",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--timbrooks--instruct-pix2pix/snapshots/31519b5cb02a7fd89b906d88731cd4d6a7bbf88d/safety_checker",
   "architectures": [
     "StableDiffusionSafetyChecker"
   ],

scheduler/scheduler_config.json

@@ -1,15 +1,23 @@
 {
-  "_class_name": "PNDMScheduler",
+  "_class_name": "EulerAncestralDiscreteScheduler",
   "_diffusers_version": "0.31.0.dev0",
+  "algorithm_type": "dpmsolver++",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
+  "dynamic_thresholding_ratio": 0.995,
+  "lower_order_final": true,
   "num_train_timesteps": 1000,
   "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
   "set_alpha_to_one": false,
   "skip_prk_steps": true,
+  "solver_order": 2,
+  "solver_type": "midpoint",
   "steps_offset": 1,
-  "timestep_spacing": "leading",
+  "thresholding": false,
+  "timestep_spacing": "linspace",
   "trained_betas": null
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "_name_or_path": "timbrooks/instruct-pix2pix",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -18,8 +18,8 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 1,
-  "projection_dim": 512,
-  "torch_dtype": "float32",
+  "projection_dim": 768,
+  "torch_dtype": "float16",
   "transformers_version": "4.45.1",
   "vocab_size": 49408
 }

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:778d02eb9e707c3fbaae0b67b79ea0d1399b52e624fb634f2f19375ae7c047c3
-size 492265168
+oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+size 246144152

unet/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.31.0.dev0",
-  "_name_or_path": "/root/autodl-tmp/model/instruct_pix2pix/checkpoint-200",
+  "_name_or_path": "timbrooks/instruct-pix2pix",
   "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:e2601d93dff82fc2de29c146a49cf5d0ff081e6f62d9b4affe023cdd3db39934
+oid sha256:a811d0c79faf160a339b0d0afa7ebaa225d673fd8c45ccf0859f4d11223d789a
 size 3438213624

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.31.0.dev0",
-  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "_name_or_path": "timbrooks/instruct-pix2pix",
   "act_fn": "silu",
   "block_out_channels": [
     128,

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d2b5932bb4151e54e694fd31ccf51fca908223c9485bd56cd0e1d83ad94c49
-size 334643268
+oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
+size 167335342