End of training

README.md

@@ -0,0 +1,65 @@
+---
+tags:
+- stable-diffusion-xl
+- stable-diffusion-xl-diffusers
+- diffusers-training
+- text-to-image
+- diffusers
+- lora
+- template:sd-lora
+widget:
+
+        - text: 'a cartoon graffiti character of TOK'
+        
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+instance_prompt: a cartoon graffiti character of TOK
+license: openrail++
+---
+
+# SDXL LoRA DreamBooth - guillepinto/pinky-lora-v5
+
+<Gallery />
+
+## Model description
+
+### These are guillepinto/pinky-lora-v5 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
+
+## Download model
+
+### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
+
+- **LoRA**: download **[`pinky-lora-v5.safetensors` here 💾](/guillepinto/pinky-lora-v5/blob/main/pinky-lora-v5.safetensors)**.
+    - Place it on your `models/Lora` folder.
+    - On AUTOMATIC1111, load the LoRA by adding `<lora:pinky-lora-v5:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
+
+
+## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
+
+pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
+pipeline.load_lora_weights('guillepinto/pinky-lora-v5', weight_name='pytorch_lora_weights.safetensors')
+
+image = pipeline('a cartoon graffiti character of TOK').images[0]
+```
+
+For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
+
+## Trigger words
+
+You should use a cartoon graffiti character of TOK to trigger the image generation.
+
+## Details
+All [Files & versions](/guillepinto/pinky-lora-v5/tree/main).
+
+The weights were trained using [🧨 diffusers Advanced Dreambooth Training Script](https://github.com/huggingface/diffusers/blob/main/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py).
+
+LoRA for the text encoder was enabled. False.
+
+Pivotal tuning was enabled: False.
+
+Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
+
+

logs/dreambooth-lora-sd-xl/1742003052.7483284/events.out.tfevents.1742003052.dee96ee77c9b.179.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c364d8dcdbd9cec5e9437b4b48851d4479a99a1ebc7f02011a94f57141ed1ce8
+size 3828

logs/dreambooth-lora-sd-xl/1742003052.7503822/hparams.yml

@@ -0,0 +1,80 @@
+adam_beta1: 0.9
+adam_beta2: 0.99
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.0001
+adam_weight_decay_text_encoder: null
+allow_tf32: false
+cache_dir: null
+cache_latents: false
+caption_column: prompt
+center_crop: false
+checkpointing_steps: 2000
+checkpoints_total_limit: null
+class_data_dir: null
+class_prompt: null
+clip_skip: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: ./pinky
+do_edm_style_training: false
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 3
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+instance_data_dir: null
+instance_prompt: a cartoon graffiti character of <s0><s1>
+learning_rate: 1.0
+local_rank: 0
+logging_dir: logs
+lora_unet_blocks: null
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_steps: 1000
+mixed_precision: fp16
+noise_offset: 0
+num_class_images: 100
+num_new_tokens_per_abstraction: 2
+num_train_epochs: 56
+num_validation_images: 4
+optimizer: prodigy
+output_dir: pinky-lora-v5
+pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
+pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
+prior_generation_precision: null
+prior_loss_weight: 1.0
+prodigy_beta3: null
+prodigy_decouple: true
+prodigy_safeguard_warmup: true
+prodigy_use_bias_correction: true
+push_to_hub: true
+random_flip: false
+rank: 8
+repeats: 1
+report_to: tensorboard
+resolution: 768
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: 0
+snr_gamma: 5.0
+text_encoder_lr: 1.0
+token_abstraction: TOK
+train_batch_size: 1
+train_text_encoder: false
+train_text_encoder_frac: 1.0
+train_text_encoder_ti: true
+train_text_encoder_ti_frac: 0.5
+use_8bit_adam: false
+use_blora: false
+use_dora: false
+validation_epochs: 50
+validation_prompt: a cartoon graffiti character of <s0><s1>, wearing a pink martial
+  arts outfit and unleashing energy blasts in a desert battlefield
+variant: null
+with_prior_preservation: false

logs/dreambooth-lora-sd-xl/events.out.tfevents.1742003052.dee96ee77c9b.179.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e1b3b208b39b9ff3b53518f03aabf15b1238a14b2cd03fb4696aec1355f621a
+size 10332006

pinky-lora-v5_emb.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73f69a82d4a3330d26b68e857916f44f9b8a77ce19d0830ecd17efb1740ce0d1
+size 16536

pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f0c35b2563f4514cf54caf7ad1c6c6f41c75f28573e68cb8b5b651c10112c1
+size 46615272