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-sylvia-boxue/models_seg_1
+
+These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning.
+You can find some example images below.
+
+prompt: Human in room
+![images_0)](./images_0.png)
+prompt: Human in room
+![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-1000/controlnet/config.json

@@ -0,0 +1,52 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.31.0.dev0",
+  "_name_or_path": "lllyasviel/control_v11p_sd15_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-1000/controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9829a31ef21926536dd6514e838019524274fe0ccee2774de47c3b3e15de61c0
+size 1445157120

checkpoint-1000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:572dec8a25b0e9c65888a26110682019e79f3d3eebd5cdb4065d1a146a8fd302
+size 2890518478

checkpoint-1000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88ec940957a9d04bc21d9aada69dcab258d1ad2bcaabfdef5b7948f81890d20c
+size 14344

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 +1,52 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.31.0.dev0",
+  "_name_or_path": "lllyasviel/control_v11p_sd15_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-500/controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26bf756bb09d5836b3a981817fea7c2876f09ff4f211945c4916a065d904c0ad
+size 1445157120

checkpoint-500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f7e048de4375ff8341e13c0933caeb1d6cd6dc0ea2fa52ba59bea8033ea099f
+size 2890518478

checkpoint-500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b8084d72ebc52287ec5b7b0d482ab6fd7086ce3becbd0180ed755b9d30213ce
+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 +1,52 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.31.0.dev0",
+  "_name_or_path": "lllyasviel/control_v11p_sd15_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 sha256:6fb06ed79b418fa089fd731bad9ac5df7470aed21481f319de65d76db193a82e
+size 1445157120

logs/train_controlnet/1724810422.528756/events.out.tfevents.1724810422.aiot-a6000-hk01.300256.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d28d821e39e9e93bfbf6b7e147bca4fcf68acc58ae85f7239b6adb47c0c01825
+size 2412

logs/train_controlnet/1724810422.5346398/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: prompt
+checkpointing_steps: 500
+checkpoints_total_limit: null
+conditioning_image_column: target
+controlnet_model_name_or_path: lllyasviel/control_v11p_sd15_seg
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: null
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+image_column: source2
+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: 1076
+mixed_precision: null
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: models_seg_1
+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: 1234
+set_grads_to_none: false
+tokenizer_name: null
+tracker_project_name: train_controlnet
+train_batch_size: 1
+train_data_dir: /home/zhiyuan/dataset
+use_8bit_adam: false
+validation_steps: 100
+variant: null

logs/train_controlnet/events.out.tfevents.1724810422.aiot-a6000-hk01.300256.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24425e835d25e8a260c96946449a6b063fbe791526332544f034a1d42761f383
+size 3074979