End of training

README.md

@@ -0,0 +1,39 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: diffusers
+license: creativeml-openrail-m
+inference: true
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- diffusers
+- textual_inversion
+- diffusers-training
+---
+
+<!-- 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. -->
+
+
+# Textual inversion text2image fine-tuning - dssr123/textual_inversion_cat
+These are textual inversion adaption weights for CompVis/stable-diffusion-v1-4. You can find some example images in the following. 
+
+
+
+
+## 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/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ca5b1f0cf856da0b0e246213e603e24c39ac9bec157695f91872b8a4c0bc455
+size 492268240

checkpoint-1000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8e747c5cee2f51f5f39942c639bf744b18dcc948242050a493a7957a40de91e
+size 303571379

checkpoint-1000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ec5e18943d8cd6d7cb95f623b820b4663c605c663a87da2d0146429fdc5bbc
+size 14821

checkpoint-1000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05eb80dfb8cbd94bf050bd473cab7f80afc068aefa77f594f4ac42f378ff6cf
+size 1401

checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9adaa3b4248360afec214daa52a7bf59f7683af19a9f83eebec6b81f787bba
+size 492268240

checkpoint-1500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c785f782626dd9815b3548539a63c185123f800761166a7d6fdee278a83ee245
+size 303571379

checkpoint-1500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17015a681bf076b924cc4e003ec04db68980baa17a97c95314e60817341ca18d
+size 14821

checkpoint-1500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae2add0d59a6a78aea6afec71f9ac3b1fa97fb833254fb6edbb645167400556b
+size 1401

checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aede9e97cc5bc78a54e6fe0d1b1e6eec4de21fd094b409fe2204c54dae8ae34c
+size 492268240

checkpoint-2000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b30f4212f3dee1da2389676a807b169cc6a3adf447422e1e5d0c67c8290423c
+size 303571379

checkpoint-2000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaeed5752c135e117ec0614699b415af40dc911860c2641ad9febeeb489a6b61
+size 14757

checkpoint-2000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f005eb939c257464d44fc9fb39c83d6f6b57b4e3e150d1788177af53e20f8431
+size 1401

checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03d5cd7ec7d6e81a2f1d51737c699aa108ed2435fe0cafb0db8c29014b302eaf
+size 492268240

checkpoint-2500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0920b48a076759f45917752d1e0706b15e1c82bddea61bafbe562f822e030906
+size 303571379

checkpoint-2500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce81b530026953e09038ea02c326a446289468ae254773372694e046fa9c04f7
+size 14821

checkpoint-2500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06165a2bc185edaa4a93aa943000a3f89f364db9b4536bffab019f56fc3f9f65
+size 1401

checkpoint-3000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e25231a8b3f11ed1a6f8f869c53d6ae66c73cb67582bcd73854c90e7a8ee7d5
+size 492268240

checkpoint-3000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c5a01326c8cc3639c1f3e3136656d54570b274bbcf486356613b4133e63c27a
+size 303571379

checkpoint-3000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:205566189010f1154e75217ec59ab4255f41994dfbbe485f56513767578d7cf3
+size 14821

checkpoint-3000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05100e81cb47a3ed38f5a92a86c5419e0adee3a9eb66da08487d987ebd01c453
+size 1401

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:372dca90946ae1b55c9ae799dea6c997062b3e20df61c18e78a7eef7cf1400fd
+size 492268240

checkpoint-500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac5acec8b8080eae475c78cf1e45a060bae3b8f1b3ac695a3d02fb59af3c4d3
+size 303571379

checkpoint-500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb1417436bc71d1732f16f04d276fcb19867e8d057d177d9b0edb62ade34a009
+size 14821

checkpoint-500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e06814c6f05382a8f45ae466e85669cce48e6ff1253c38b561440a8decaf2685
+size 1401

feature_extractor/preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

learned_embeds-steps-1000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7293dc8af418d6563401a9a7248c1190f6ea30c6484f9605c69199d848acbc99
+size 3184

learned_embeds-steps-1500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945f8ccc650b135f91a75f3a67749e6284f53b929b19c62b8d838015ceb4b1d3
+size 3184

learned_embeds-steps-2000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aadc533a0371eda3b4e561b7850f3123ef0245d872c6354bcf88f4faed80408
+size 3184

learned_embeds-steps-2500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9dc26b919c386e5f50a560747429d4c85df0b86984cee8fd1903c964fe3f09e
+size 3184

learned_embeds-steps-3000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a365934f848a37b9abba95bd92a5438a163e5f4d81662dad1149c859c0476889
+size 3184

learned_embeds-steps-500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:153569741c2727afd5c490517dea251310423400d84590fb9d96313ea2a03b7f
+size 3184

learned_embeds.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a365934f848a37b9abba95bd92a5438a163e5f4d81662dad1149c859c0476889
+size 3184

logs/textual_inversion/1747486755.9734285/events.out.tfevents.1747486755.DESKTOP-CEVB4GL.41020.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:946ec5b6aef7f8598be61998722d539120021eb53f37c4264912034ed95c7e3b
+size 2321

logs/textual_inversion/1747486755.9764285/hparams.yml

@@ -0,0 +1,48 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+initializer_token: toy
+learnable_property: object
+learning_rate: 0.002
+local_rank: -1
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 3000
+mixed_precision: 'no'
+no_safe_serialization: false
+num_train_epochs: 18
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_cat
+placeholder_token: <cattoy>
+pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
+push_to_hub: true
+repeats: 100
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: false
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 1
+train_data_dir: ./cat
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100
+variant: null

logs/textual_inversion/1747486845.8222208/events.out.tfevents.1747486845.DESKTOP-CEVB4GL.40472.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f5684c91fe942f54f16c6320379c240992f26df6c45031d9e7174edaf3341f
+size 2321

logs/textual_inversion/1747486845.825223/hparams.yml

@@ -0,0 +1,48 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+initializer_token: toy
+learnable_property: object
+learning_rate: 0.002
+local_rank: -1
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 3000
+mixed_precision: 'no'
+no_safe_serialization: false
+num_train_epochs: 20
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_cat
+placeholder_token: <cattoy>
+pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
+push_to_hub: true
+repeats: 100
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: false
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 1
+train_data_dir: ./cat
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100
+variant: null

logs/textual_inversion/1747549608.6569357/events.out.tfevents.1747549608.DESKTOP-CEVB4GL.16364.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d853a575e337ee41f71bff43cbb1f1ef2bc1acde50c12678a6e02467cec6dbbb
+size 2321

logs/textual_inversion/1747549608.6599357/hparams.yml

@@ -0,0 +1,48 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+initializer_token: toy
+learnable_property: object
+learning_rate: 0.002
+local_rank: -1
+logging_dir: logs
+lr_num_cycles: 1
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_train_steps: 3000
+mixed_precision: 'no'
+no_safe_serialization: false
+num_train_epochs: 20
+num_validation_images: 4
+num_vectors: 1
+output_dir: textual_inversion_cat
+placeholder_token: <cattoy>
+pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
+push_to_hub: true
+repeats: 100
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+save_as_full_pipeline: false
+save_steps: 500
+scale_lr: true
+seed: null
+tokenizer_name: null
+train_batch_size: 1
+train_data_dir: ./cat
+validation_epochs: null
+validation_prompt: null
+validation_steps: 100
+variant: null

logs/textual_inversion/events.out.tfevents.1747486755.DESKTOP-CEVB4GL.41020.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb76c11d04300c1229b015e67e0bff39af1d2603ae1cd78705c311e398ab365a
+size 2946

logs/textual_inversion/events.out.tfevents.1747486845.DESKTOP-CEVB4GL.40472.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65448e50e9b354a3addb96d2009a5997d0424855d206c5a1d8a8d9e585967d5a
+size 1007054

logs/textual_inversion/events.out.tfevents.1747549608.DESKTOP-CEVB4GL.16364.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d79868614870c50fa7d499a3a8f7026ecc0eecdcc72b1ace213627ca21790844
+size 1007054

model_index.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.34.0.dev0",
+  "_name_or_path": "CompVis/stable-diffusion-v1-4",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

safety_checker/config.json

@@ -0,0 +1,47 @@
+{
+  "architectures": [
+    "StableDiffusionSafetyChecker"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 77,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "projection_dim": 512,
+    "torch_dtype": "float32",
+    "vocab_size": 49408
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "layer_norm_eps": 1e-05,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 512,
+    "torch_dtype": "float32"
+  }
+}

safety_checker/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
+size 1215979664

scheduler/scheduler_config.json

@@ -0,0 +1,15 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.34.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "vocab_size": 49409
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e25231a8b3f11ed1a6f8f869c53d6ae66c73cb67582bcd73854c90e7a8ee7d5
+size 492268240

tokenizer/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<cattoy>": 49408
+}