End of training

README.md

@@ -0,0 +1,44 @@
+---
+base_model: nroggendorff/animexl
+library_name: diffusers
+license: creativeml-openrail-m
+tags:
+- stable-diffusion-xl
+- stable-diffusion-xl-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 - nroggendorff/zelda-lora
+
+These are LoRA adaption weights for nroggendorff/animexl. The weights were fine-tuned on the nroggendorff/zelda dataset. You can find some example images in the following. 
+
+
+
+LoRA for the text encoder was enabled: False.
+
+Special VAE used for training: None.
+
+
+## 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/1721347319.8772824/events.out.tfevents.1721347319.r-nroggendorff-train-lora-c6va1q4t-82c48-yyslv.69.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e9776cded8f31d287d72c65d66ed61ad617533b7ccff4793a500ad608bffdb6
+size 2257

logs/text2image-fine-tune/1721347319.8786275/hparams.yml

@@ -0,0 +1,53 @@
+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: 100000
+checkpoints_total_limit: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: nroggendorff/zelda
+debug_loss: false
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+learning_rate: 1.0e-05
+local_rank: -1
+logging_dir: logs
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: null
+max_train_steps: 150
+mixed_precision: fp16
+noise_offset: 0
+num_train_epochs: 11
+num_validation_images: 4
+output_dir: zelda-lora
+prediction_type: null
+pretrained_model_name_or_path: nroggendorff/animexl
+pretrained_vae_model_name_or_path: null
+push_to_hub: true
+random_flip: true
+rank: 4
+report_to: tensorboard
+resolution: 1024
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: null
+snr_gamma: null
+train_batch_size: 8
+train_data_dir: null
+train_text_encoder: false
+use_8bit_adam: false
+validation_epochs: 1
+validation_prompt: null
+variant: null

logs/text2image-fine-tune/events.out.tfevents.1721347319.r-nroggendorff-train-lora-c6va1q4t-82c48-yyslv.69.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f006f3729948d331519ba21c34b4ec4331fcbdbebcfcbee7a6ebc0935e8d1fd
+size 7311

pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3e71abe28129f28866c90edad4cf567b985a4230016f3dc7f1fd9b82f1c87a
+size 23390424