End of training

README.md

@@ -0,0 +1,45 @@
+---
+base_model: runwayml/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-jiang0203/save
+
+These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning.
+You can find some example images below.
+
+prompt: The screenshot is very likely an editor app. You can see a functionality to edit or create content. You may notice a web view located at the center area which you can do click. A web view is a component that displays website content.
+![images_0)](./images_0.png)
+prompt: The interface looks like a modal app. You can see a popup window with additional content. You can find a text placed at the center area of the screen.
+![images_1)](./images_1.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]

checkpoint-10000/controlnet/config.json

@@ -0,0 +1,52 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.30.0.dev0",
+  "_name_or_path": "lllyasviel/sd-controlnet-seg",
+  "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-10000/controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a9e7084db34977313791173d3ad36eed94ed25da26ea9e32300fb24db8899ea
+size 1445157120

checkpoint-10000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d72a01691214af9929450cbd924726b34d56f8744ab2376749891c6604c6ce5
+size 725253818

checkpoint-10000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7990ec051edcb9aced68dcfe89974b3fd4ae3184ae4c1e50181762cb8dbcbb6e
+size 14344

checkpoint-10000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d49367aa0f19981d0484e3ef5c1b009e6bdd8e5c0d8ef08f2f8d235b9f843816
+size 988

checkpoint-10000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d31ad9a5150e341b638f838a47b3cb3db0d48efa493bcc8d1f8bf787b2c8cee3
+size 1000

checkpoint-15000/controlnet/config.json

@@ -0,0 +1,52 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.30.0.dev0",
+  "_name_or_path": "lllyasviel/sd-controlnet-seg",
+  "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-15000/controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a33cb46a6c4b9219fd4e9735171a564f1900683ea437459d8ddbb73dd71027a
+size 1445157120

checkpoint-15000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b464fd1c0222f1c9adef560d5705e09cf013ce9fe3235ff739e9381b35bcfbed
+size 725253818

checkpoint-15000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17ef2585508461076d6f33d53ab0a7fdef9962203daa630eb06e12fd4f19d71f
+size 14344

checkpoint-15000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f72e56eb22a4ba07bb72f88ef4e0f6e651d8d95136d0f1160d6dd591030a505e
+size 988

checkpoint-15000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43886888e1722042a359e3f05d5781f51e922aa7d8eed2a7fc8147f7b6d3b813
+size 1000

checkpoint-5000/controlnet/config.json

@@ -0,0 +1,52 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.30.0.dev0",
+  "_name_or_path": "lllyasviel/sd-controlnet-seg",
+  "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-5000/controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d911ede2b197969f8b1bf06acd7df8f729ec7602e910b9a4b5e1482a00477bf
+size 1445157120

checkpoint-5000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:518dd20f207a495113034e4478493cd30970376405f5b357a6a776f765cfd732
+size 725253818

checkpoint-5000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e64ab8900002cd8e2c2aede7e44271307c698933b97883918830a5df6359b3a
+size 14344

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 sha256:920333155b08e76154b89a85170c320833074db7b84649a9cfe79fd10b6bf2d9
+size 1000

config.json

@@ -0,0 +1,52 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.30.0.dev0",
+  "_name_or_path": "lllyasviel/sd-controlnet-seg",
+  "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 sha256:207018df40e85662e05f42ff6ef06254cf66e8014ff0363aeb406ebb5ae1d424
+size 1445157120

logs/train_controlnet/1719580651.4336507/events.out.tfevents.1719580651.DESKTOP-SEAR6UM.12896.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d035c2e8626a57a92a26c583c9313563d3cf62732cbaaf1953d7d1e4388b297c
+size 2411

logs/train_controlnet/1719580651.4350693/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: text
+checkpointing_steps: 500
+checkpoints_total_limit: null
+conditioning_image_column: conditioning_image
+controlnet_model_name_or_path: lllyasviel/sd-controlnet-seg
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: /home/jiang/BoostingGUI/UIdataset
+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: 5471
+mixed_precision: null
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: /home/jiang/BoostingGUI/save
+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: 1
+train_data_dir: null
+use_8bit_adam: false
+validation_steps: 100
+variant: null

logs/train_controlnet/1719581219.5309868/events.out.tfevents.1719581219.DESKTOP-SEAR6UM.14851.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f3f6966cdbe6e2c0bf24e291771397d7c14acdc93329bc0e05fde6d23323dc
+size 2411

logs/train_controlnet/1719581219.5324168/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: text
+checkpointing_steps: 500
+checkpoints_total_limit: null
+conditioning_image_column: conditioning_image
+controlnet_model_name_or_path: lllyasviel/sd-controlnet-seg
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: /home/jiang/BoostingGUI/UIdataset
+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: 5471
+mixed_precision: null
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: /home/jiang/BoostingGUI/save
+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: 1
+train_data_dir: null
+use_8bit_adam: false
+validation_steps: 100
+variant: null

logs/train_controlnet/events.out.tfevents.1719580651.DESKTOP-SEAR6UM.12896.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b6c3a0d8bebbfa0c2e1e95a1ba27a567c18dce6372b8600d76d56ddf91df6cd
+size 32794

logs/train_controlnet/events.out.tfevents.1719581219.DESKTOP-SEAR6UM.14851.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd7c1fdf311fdc328d8fc0b6351a33b1637de8188dd12b8808dda69797774ed
+size 32794