End of training

.gitattributes

@@ -33,3 +33,7 @@ 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
+images_1.png filter=lfs diff=lfs merge=lfs -text
+images_2.png filter=lfs diff=lfs merge=lfs -text
+images_3.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,49 @@
+---
+license: creativeml-openrail-m
+library_name: diffusers
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- diffusers
+- controlnet
+- diffusers-training
+base_model: runwayml/stable-diffusion-v1-5
+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-EpsilonGreedy/Clothes2Person0.0010.5
+
+These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning.
+You can find some example images below.
+
+prompt: C2PDress, a woman, refracted line and sparkles, bold graphics, suki, barcodes, gliter, round-cropped, flat texture, galactic, palladium, lower part of face, stands in front of a white background
+![images_0)](./images_0.png)
+prompt: C2PUpperBody, a woman wearing black leather skirt, anthro, minimalist photorealist, t-top, pelisse, a new, features between french, inspired by James Baynes, flat icon, oppai, cut out, very ahestetic, stands in front of a white background
+![images_1)](./images_1.png)
+prompt: C2PLowerBody, a woman in a black top with a black jacket, elegant cape, wearing a cropped top, 4 arms, posh, cloth sim, inspired by Rose ONeill, listing image, proportions off, bubblegum, lower part of face, stands in front of a white background
+![images_2)](./images_2.png)
+prompt: C2PUpperBody, a man in tan shorts standing in front of a white wall, discord moderator, round-cropped, summer vibrance, simplified, dividing it into nine quarters, sculls, scandinavian style, nbc, lower part of face, stands in front of a white background
+![images_3)](./images_3.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-2500/controlnet/config.json

@@ -0,0 +1,51 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.30.0.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-2500/controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acddfb87e5d885afcf60e17fff68f0786331ea5259ea413b848806ce8518229b
+size 1445157120

checkpoint-2500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c40dbb461c782df458484f31fa1c18dcc2cb61bc603734dc23d5d4c547a89e5
+size 725253818

checkpoint-2500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5513c47aa21e1d0ade1c9efae2f3b396089716771644cd51df70b67a431ff416
+size 14604

checkpoint-2500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f346a90a57b593d51bff4b78388f1c65124ce868185b7af6ea7ccf14d0e8c90e
+size 1000

config.json

@@ -0,0 +1,51 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.30.0.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:b59b984c375d76f7c856dd27e6390faef47cc0e660ca17f413d07b7c7dcde8ab
+size 1445157120

logs/train_controlnet/1720104021.3402421/events.out.tfevents.1720104021.4c7d08e78dfc.110.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008a33624c3d9c1c4da9f15ec2ba4ef542a0eb976e00d80be44866d12a557c78
+size 2465

logs/train_controlnet/1720104021.342703/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: 2500
+checkpoints_total_limit: null
+conditioning_image_column: conditioning_image
+controlnet_model_name_or_path: null
+dataloader_num_workers: 4
+dataset_config_name: null
+dataset_name: EpsilonGreedy/Clothes2Person
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: EpsilonGreedy/Clothes2Person0.0010.5
+hub_token: null
+image_column: image
+learning_rate: 0.001
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant_with_warmup
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 2812
+mixed_precision: null
+num_train_epochs: 1
+num_validation_images: 4
+output_dir: /kaggle/working/output/Clothes2Person
+pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
+proportion_empty_prompts: 0.5
+push_to_hub: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+scale_lr: false
+seed: null
+set_grads_to_none: false
+tokenizer_name: null
+tracker_project_name: train_controlnet
+train_batch_size: 3
+train_data_dir: null
+use_8bit_adam: true
+validation_steps: 2500
+variant: null

logs/train_controlnet/events.out.tfevents.1720104021.4c7d08e78dfc.110.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5c229ba294c233f99642c224da84093644a0b8dd78bb4fe85f0864091f906d
+size 13710518