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
+image_0.png filter=lfs diff=lfs merge=lfs -text
+image_1.png filter=lfs diff=lfs merge=lfs -text
+image_2.png filter=lfs diff=lfs merge=lfs -text
+image_3.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,97 @@
+---
+tags:
+- stable-diffusion-xl
+- stable-diffusion-xl-diffusers
+- diffusers-training
+- text-to-image
+- diffusers
+- lora
+- template:sd-lora
+widget:
+
+        - text: 'A Poro situated in a red sky, war scenario. The Poro wears a brown cape. Region of Shurima. In <s0><s1> style.'
+          output:
+            url:
+                "image_0.png"
+        
+        - text: 'A Poro situated in a red sky, war scenario. The Poro wears a brown cape. Region of Shurima. In <s0><s1> style.'
+          output:
+            url:
+                "image_1.png"
+        
+        - text: 'A Poro situated in a red sky, war scenario. The Poro wears a brown cape. Region of Shurima. In <s0><s1> style.'
+          output:
+            url:
+                "image_2.png"
+        
+        - text: 'A Poro situated in a red sky, war scenario. The Poro wears a brown cape. Region of Shurima. In <s0><s1> style.'
+          output:
+            url:
+                "image_3.png"
+        
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+instance_prompt: In <s0><s1> style.
+license: openrail++
+---
+
+# SDXL LoRA DreamBooth - BruBel/lor-style-training-v6
+
+<Gallery />
+
+## Model description
+
+### These are BruBel/lor-style-training-v6 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 **[`lor-style-training-v6.safetensors` here 💾](/BruBel/lor-style-training-v6/blob/main/lor-style-training-v6.safetensors)**.
+    - Place it on your `models/Lora` folder.
+    - On AUTOMATIC1111, load the LoRA by adding `<lora:lor-style-training-v6:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
+- *Embeddings*: download **[`lor-style-training-v6_emb.safetensors` here 💾](/BruBel/lor-style-training-v6/blob/main/lor-style-training-v6_emb.safetensors)**.
+    - Place it on it on your `embeddings` folder
+    - Use it by adding `lor-style-training-v6_emb` to your prompt. For example, `In lor-style-training-v6_emb style.`
+    (you need both the LoRA and the embeddings as they were trained together for this LoRA)
+    
+
+## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
+from huggingface_hub import hf_hub_download
+from safetensors.torch import load_file
+        
+pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
+pipeline.load_lora_weights('BruBel/lor-style-training-v6', weight_name='pytorch_lora_weights.safetensors')
+embedding_path = hf_hub_download(repo_id='BruBel/lor-style-training-v6', filename='lor-style-training-v6_emb.safetensors', repo_type="model")
+state_dict = load_file(embedding_path)
+pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
+pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
+        
+image = pipeline('A Poro situated in a red sky, war scenario. The Poro wears a brown cape. Region of Shurima. In <s0><s1> style.').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
+
+To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:
+
+to trigger concept `LEGENDSOFRUNETERRA` → use `<s0><s1>` in your prompt 
+
+
+
+## Details
+All [Files & versions](/BruBel/lor-style-training-v6/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: True.
+
+Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
+
+

checkpoint-10000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b71b55b93964093a8c2b22e3a08aa06080d018fa390a9342325c4a1bfa06df13
+size 1182072760

checkpoint-10000/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c74650a6dde630e075b591a1626250444a09993ce8b1108c7ef889a6faabeb23
+size 185964888

checkpoint-10000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:201045b36031a1cf06acac30fc15fee42b1ad3972f9824734e19a9c9b3f6ba25
+size 14408

checkpoint-10000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcc150ecb5350ee944d6ece70445c822aed2b29c2785d6660ba82247100862dc
+size 1064

checkpoint-20000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a6c91fc083200da6f011132d213ad60b6ed98000c69c1219eae0f7faf730fc3
+size 1182072760

checkpoint-20000/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f94d7514676a8bdb2481af960f63e62ba5c8b954572ed46ae925f3be59e2fa10
+size 185964888

checkpoint-20000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed548937b7052ff0b9fcf9ce14156e943aebcf9c8d33a5d649b5807d1152837
+size 14408

checkpoint-20000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f615bccb0e7a5fa7fda853938ae9cea097a23cc186f8602265b8e2a6a835adf
+size 1064

checkpoint-30000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b784f83d37150fdafdf102eef381f031c4824c7253feb69d32db800a507bf953
+size 1182072760

checkpoint-30000/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c6da8aecbfdb9325bfb0ff4304d53e8b36892f0989e81a9026b2340dc44bac9
+size 185964888

checkpoint-30000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14215f755551527cbb4a12d33823895eb3d261fd24e02d5bffbf27dc81df2376
+size 14408

checkpoint-30000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b4b0a40f4ca18f123f3c0c1c3c7a0a40f5dc76979d956d08d1ec2c1ff5eee1
+size 1064

logs/dreambooth-lora-sd-xl/1727905570.2759311/events.out.tfevents.1727905570.50c876563f2c.4524.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:137001dce5850070ddb0a783268e1037e01bf0076f01b9d38e7532551f9c6f4c
+size 3867

logs/dreambooth-lora-sd-xl/1727905570.2780905/hparams.yml

@@ -0,0 +1,80 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+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: 10000
+checkpoints_total_limit: null
+class_data_dir: null
+class_prompt: style
+clip_skip: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: BruBel/lor-style-training
+do_edm_style_training: false
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+instance_data_dir: null
+instance_prompt: In <s0><s1> style.
+learning_rate: 0.0001
+local_rank: -1
+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: 30000
+mixed_precision: bf16
+noise_offset: 0
+num_class_images: 100
+num_new_tokens_per_abstraction: 2
+num_train_epochs: 2000
+num_validation_images: 4
+optimizer: AdamW
+output_dir: lor-style-training-v6
+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: 64
+repeats: 1
+report_to: tensorboard
+resolution: 1024
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: 1
+snr_gamma: 5.0
+text_encoder_lr: 0.0003
+token_abstraction: LEGENDSOFRUNETERRA
+train_batch_size: 7
+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 Poro situated in a red sky, war scenario. The Poro wears a brown
+  cape. Region of Shurima. In <s0><s1> style.
+variant: null
+with_prior_preservation: false

logs/dreambooth-lora-sd-xl/events.out.tfevents.1727905570.50c876563f2c.4524.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf510bd1bb8283f90c06e0ba516e3f70e09ff72ced060264b734274a921708e
+size 226151577

lor-style-training-v6.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6203821e3e2a4ff9dac647c94b8313e67468a698557598b7d06b38e0b2aeaf
+size 371841776

lor-style-training-v6_emb.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8abf4463b21dd6001f0760b8bcefb22058f9e7888c7757a795eaaba80a3f2e27
+size 16536

pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc513240edc71312102e1ab2dce0e451b782cc111f1fc018cee2908850a16ae3
+size 371758976