End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+images_0.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,43 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: diffusers
+license: creativeml-openrail-m
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- diffusers
+- controlnet
+- diffusers-training
+inference: true
+---
+
+<!-- This model card has been generated automatically according to the information the training script had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+
+# controlnet-wlllllllly/output_cval
+
+These are controlnet weights trained on stable-diffusion-v1-5/stable-diffusion-v1-5 with new type of conditioning.
+You can find some example images below.
+
+prompt: The segmentation mask
+![images_0)](./images_0.png)
+
+
+
+## Intended uses & limitations
+
+#### How to use
+
+```python
+# TODO: add an example code snippet for running this diffusion pipeline
+```
+
+#### Limitations and bias
+
+[TODO: provide examples of latent issues and potential remediations]
+
+## Training details
+
+[TODO: describe the data used to train the model]

config.json

@@ -0,0 +1,51 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.31.0.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:febda2ebb6c69a3d7d86c7bb9d146c6e7cb843a1d1c1540801044ea4e85f44c6
+size 1445157120

logs/train_controlnet/1729178531.5154834/events.out.tfevents.1729178531.ntuh.1196806.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4db7c6a96c05c15e0c565e416b17af3882a3e57a60dbb12d25e4e737b7b295
+size 2363

logs/train_controlnet/1729178531.5199413/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: additional_feature
+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: null
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+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: 2
+mixed_precision: null
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: ./output_cval
+pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+proportion_empty_prompts: 0
+push_to_hub: false
+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: 4
+train_data_dir: /home/wly/HD/code/diffuser_ex/diffusers/examples/controlnet/cvai_test
+use_8bit_adam: false
+validation_steps: 100
+variant: null

logs/train_controlnet/1729178611.2519412/events.out.tfevents.1729178611.ntuh.1197783.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5f45854da5b35f5b889228106ba378e45fd07d882933ec16a8bb501baa506eb
+size 2363

logs/train_controlnet/1729178611.255771/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: additional_feature
+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: null
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+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: 2
+mixed_precision: null
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: ./output_cval
+pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+proportion_empty_prompts: 0
+push_to_hub: false
+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: 4
+train_data_dir: /home/wly/HD/code/diffuser_ex/diffusers/examples/controlnet/cvai_test
+use_8bit_adam: false
+validation_steps: 100
+variant: null

logs/train_controlnet/1729178656.8071141/events.out.tfevents.1729178656.ntuh.1198472.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d2cf8a3d4aa5d84dbb23ff060e0107fd49b2ea4093206c63deee4cad0af0ca
+size 2363

logs/train_controlnet/1729178656.8116872/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: additional_feature
+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: null
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+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: 2
+mixed_precision: null
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: ./output_cval
+pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+proportion_empty_prompts: 0
+push_to_hub: false
+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: 4
+train_data_dir: /home/wly/HD/code/diffuser_ex/diffusers/examples/controlnet/cvai_test
+use_8bit_adam: false
+validation_steps: 100
+variant: null

logs/train_controlnet/1729178729.4820194/events.out.tfevents.1729178729.ntuh.1199241.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6d8115c102f9176e5259c8a093f0abc3b7bda32050320f9bc35fe066367b032
+size 2363

logs/train_controlnet/1729178729.5058472/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: additional_feature
+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: null
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+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: 2
+mixed_precision: null
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: ./output_cval
+pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+proportion_empty_prompts: 0
+push_to_hub: false
+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: 4
+train_data_dir: /home/wly/HD/code/diffuser_ex/diffusers/examples/controlnet/cvai_test
+use_8bit_adam: false
+validation_steps: 100
+variant: null

logs/train_controlnet/1729178884.7533236/events.out.tfevents.1729178884.ntuh.1200800.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7da49cfd6b44b69ad667f83a874946ebeb381e33105920d71075f636330b53c
+size 2363

logs/train_controlnet/1729178884.7610114/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: additional_feature
+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: null
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+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: 2
+mixed_precision: null
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: ./output_cval
+pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+proportion_empty_prompts: 0
+push_to_hub: false
+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: 4
+train_data_dir: /home/wly/HD/code/diffuser_ex/diffusers/examples/controlnet/cvai_test
+use_8bit_adam: false
+validation_steps: 100
+variant: null

logs/train_controlnet/1729179270.135104/events.out.tfevents.1729179270.ntuh.1204616.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d93044ace8ec232bb1d1b05a622f11dd40791405eee896118c438acd5a2efaf
+size 2363

logs/train_controlnet/1729179270.1369576/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: additional_feature
+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: null
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+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: 2
+mixed_precision: null
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: ./output_cval
+pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+proportion_empty_prompts: 0
+push_to_hub: false
+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: 4
+train_data_dir: /home/wly/HD/code/diffuser_ex/diffusers/examples/controlnet/cvai_test
+use_8bit_adam: false
+validation_steps: 100
+variant: null

logs/train_controlnet/1729179486.9656248/events.out.tfevents.1729179486.ntuh.1206792.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce4a3f041e064c68da0c69dd616a6729a0b9eaa917f5b021da6b4dd22619605
+size 2363

logs/train_controlnet/1729179486.9977713/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: additional_feature
+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: null
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+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: 2
+mixed_precision: null
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: ./output_cval
+pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-v1-5
+proportion_empty_prompts: 0
+push_to_hub: false
+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: 4
+train_data_dir: /home/wly/HD/code/diffuser_ex/diffusers/examples/controlnet/cvai_test
+use_8bit_adam: false
+validation_steps: 100
+variant: null

logs/train_controlnet/1729183504.7271576/events.out.tfevents.1729183504.ntuh.1244188.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7f553337404df685795cabf9513c2a8a0e6feba67c913e99f77fbd5c7b4f7f7
+size 2363

logs/train_controlnet/1729183504.7466714/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: additional_feature
+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: null
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+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: 2
+mixed_precision: null
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: ./output_cval
+pretrained_model_name_or_path: stable-diffusion-v1-5/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: 4
+train_data_dir: /home/wly/HD/code/diffuser_ex/diffusers/examples/controlnet/cvai_test
+use_8bit_adam: false
+validation_steps: 100
+variant: null

logs/train_controlnet/1729183591.016311/events.out.tfevents.1729183591.ntuh.1245316.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfaa547eaa21b5b8d20452fb0830f92d5f14b5ef6e1f3c999e647744ff77440b
+size 2363

logs/train_controlnet/1729183591.018318/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: additional_feature
+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: null
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+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: 2
+mixed_precision: null
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: ./output_cval
+pretrained_model_name_or_path: stable-diffusion-v1-5/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: 4
+train_data_dir: /home/wly/HD/code/diffuser_ex/diffusers/examples/controlnet/cvai_test
+use_8bit_adam: false
+validation_steps: 100
+variant: null

logs/train_controlnet/events.out.tfevents.1729178531.ntuh.1196806.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cea4dbddd733dcd1ca82b7f4407f5777f5c9571e53037db226be6985b3a479e
+size 88

logs/train_controlnet/events.out.tfevents.1729178611.ntuh.1197783.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd31f5f59d98e2e1e82eb1cbbbc6004723222ea6ae89d6f8eacb63120db6df0
+size 88

logs/train_controlnet/events.out.tfevents.1729178656.ntuh.1198472.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc359fc7dff85993cec6a8b3ca1aecb97cd476a04bab5923e646eb3b0c6399e4
+size 88

logs/train_controlnet/events.out.tfevents.1729178729.ntuh.1199241.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f955fd799f5bdb9f317b46195de96721249cff1520e79aed6fb1214f45041a60
+size 88

logs/train_controlnet/events.out.tfevents.1729178884.ntuh.1200800.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:208bece6ff805c241be5d854c2bf3bb25b3cf651cf1e1b20c94136f220419b23
+size 4331281

logs/train_controlnet/events.out.tfevents.1729179270.ntuh.1204616.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb3abf947840720c87b06a96493f16842c6fac5a36a602fdcf16050e149ef794
+size 252

logs/train_controlnet/events.out.tfevents.1729179486.ntuh.1206792.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8432435204ddc41cc406a89f8d872e3feb9876c5c9bd0d1b5c58363e6c09b05
+size 252

logs/train_controlnet/events.out.tfevents.1729183504.ntuh.1244188.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39ba5aa8704fa331091ade88025e23149e1371796986d9e1336b240a5bde1605
+size 252

logs/train_controlnet/events.out.tfevents.1729183591.ntuh.1245316.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22277dee93a240b618fca6012f15ac61c39aeddce1eee42dec98cdbcc7148951
+size 1964259