End of training

README.md

@@ -0,0 +1,17 @@
+
+---
+license: creativeml-openrail-m
+base_model: runwayml/stable-diffusion-v1-5
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- diffusers
+- controlnet
+inference: true
+---
+    
+# controlnet-AmrutaMuthal/mero_controlnet_scaled_filled_boxes_lr1
+
+These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning.
+

checkpoint-1000/controlnet/config.json

@@ -0,0 +1,51 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.26.0.dev0",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_channels": 3,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "global_pool_conditions": false,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "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,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_time_scale_shift": "default",
+  "transformer_layers_per_block": 1,
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

checkpoint-1000/controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b44b96695df5f3dad89d23eaf456256e1eda3ad3e8ca181904b83855a4f3e7e2
+size 1445157120

checkpoint-1000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b730254d93f1cbe8a97a863c1be08c0a5caa6857f0e060e805b66b5aaf1b2d
+size 2890518478

checkpoint-1000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:961f7c67a6fec914bf8f03c21103075f00d9b7b0ac0fc641e6a9227a61ebd7e4
+size 14408

checkpoint-1000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d16ae9dedf4c45ceadc467593037d83423677715e75ab402a9f44aa81de9b84
+size 1000

checkpoint-500/controlnet/config.json

@@ -0,0 +1,51 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.26.0.dev0",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_channels": 3,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "global_pool_conditions": false,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "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,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_time_scale_shift": "default",
+  "transformer_layers_per_block": 1,
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

checkpoint-500/controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4690d125e66edb8cdc54f3e9c80197c2d6e2d0bdd7ad6f3e9e5b10d7369e7588
+size 1445157120

checkpoint-500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc904509d7b052d65f725bedcfb618cd938f8e8ef0458748658705ae6183e6c
+size 2890518478

checkpoint-500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c014c21fe6cbcb03f03478b6bd385ef638e0b6779c02c3e1b7a22a78794bc9af
+size 14344

checkpoint-500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68d7b85c46d195e3cd6e587d94878d77f315e0a073acfab811251f39fbe891fc
+size 1000

config.json

@@ -0,0 +1,51 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.26.0.dev0",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_channels": 3,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "global_pool_conditions": false,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "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,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_time_scale_shift": "default",
+  "transformer_layers_per_block": 1,
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7599a3c4ca5ea8e0457a6ed92ae75d0584a2290c2e8c6effdde8730f59c9bc1d
+size 1445157120

logs/train_controlnet/1707031470.0306032/events.out.tfevents.1707031470.d93b6cbc917b.30223.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e12f665fa259238dd2ad1c28751ed325d4c545d3502e30db6fac91678666698
+size 2361

logs/train_controlnet/1707031470.0324347/hparams.yml

@@ -0,0 +1,50 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+cache_dir: null
+caption_column: caption
+checkpointing_steps: 500
+checkpoints_total_limit: null
+conditioning_image_column: conditioning_image
+controlnet_model_name_or_path: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: AmrutaMuthal/controlnet_layout2image_scaled_filled_boxes
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+image_column: image
+learning_rate: 1.0e-05
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 1250
+mixed_precision: null
+num_train_epochs: 2
+num_validation_images: 4
+output_dir: AmrutaMuthal/mero_controlnet_scaled_filled_boxes_lr1
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+proportion_empty_prompts: 0
+push_to_hub: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: null
+set_grads_to_none: false
+tokenizer_name: null
+tracker_project_name: train_controlnet
+train_batch_size: 8
+train_data_dir: null
+use_8bit_adam: false
+validation_steps: 100
+variant: null

logs/train_controlnet/events.out.tfevents.1707031470.d93b6cbc917b.30223.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1594eedff07119169d160ca6604ba8185482c1e405674f41bdc0e571f0ceb2df
+size 419054