End of training

README.md

@@ -0,0 +1,43 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: diffusers
+license: creativeml-openrail-m
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- diffusers
+- diffusers-training
+- lora
+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. -->
+
+
+# LoRA text2image fine-tuning - ars1122/samsung-lora
+These are LoRA adaption weights for CompVis/stable-diffusion-v1-4. The weights were fine-tuned on the ars1122/samsung-phones-dataset dataset. You can find some example images in the following. 
+
+![img_0](./image_0.png)
+![img_1](./image_1.png)
+![img_2](./image_2.png)
+![img_3](./image_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]

logs/text2image-fine-tune/1727101450.9583447/events.out.tfevents.1727101450.3a59fa0a73ab.154.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7092d48625e5e1f0467516796cd42f44aba7120414f03ef9ae6b6aeb5ca55491
+size 2281

logs/text2image-fine-tune/1727101450.9605014/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
+center_crop: true
+checkpointing_steps: 500
+checkpoints_total_limit: null
+dataloader_num_workers: 4
+dataset_config_name: null
+dataset_name: ars1122/samsung-phones-dataset
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+hub_model_id: samsung-lora
+hub_token: null
+image_column: image
+learning_rate: 0.0001
+local_rank: -1
+logging_dir: logs
+lr_scheduler: cosine
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 20
+mixed_precision: null
+noise_offset: 0
+num_train_epochs: 10
+num_validation_images: 4
+output_dir: /kaggle/working/
+prediction_type: null
+pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
+push_to_hub: true
+random_flip: true
+rank: 4
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: 1337
+snr_gamma: null
+train_batch_size: 1
+train_data_dir: null
+use_8bit_adam: false
+validation_epochs: 1
+validation_prompt: samsung galaxy a35
+variant: null

logs/text2image-fine-tune/events.out.tfevents.1727101450.3a59fa0a73ab.154.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8383787faf389628a7d4fe12e74571c5800dfd6d689ef9099efb0bda30f658e3
+size 19804650

pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d47af7a5e9536fcced3e4d23b7fa6f5335fe5468dd38dad1638be8d89e4cc240
+size 3226184