End of training

README.md

@@ -0,0 +1,95 @@
+---
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- diffusers-training
+- text-to-image
+- diffusers
+- lora
+- template:sd-lora
+widget:
+
+        - text: '<pokemon> with white background'
+          output:
+            url:
+                "image_0.png"
+        
+        - text: '<pokemon> with white background'
+          output:
+            url:
+                "image_1.png"
+        
+        - text: '<pokemon> with white background'
+          output:
+            url:
+                "image_2.png"
+        
+        - text: '<pokemon> with white background'
+          output:
+            url:
+                "image_3.png"
+        
+base_model: emilianJR/epiCRealism
+instance_prompt: <pokemon>
+license: openrail++
+---
+
+# SD1.5 LoRA DreamBooth - wannyansports/sdpokemon
+
+<Gallery />
+
+## Model description
+
+### These are wannyansports/sdpokemon LoRA adaption weights for emilianJR/epiCRealism.
+
+## Download model
+
+### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
+
+- **LoRA**: download **[`sdpokemon.safetensors` here 💾](/wannyansports/sdpokemon/blob/main/sdpokemon.safetensors)**.
+    - Place it on your `models/Lora` folder.
+    - On AUTOMATIC1111, load the LoRA by adding `<lora:sdpokemon:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
+- *Embeddings*: download **[`sdpokemon_emb.safetensors` here 💾](/wannyansports/sdpokemon/blob/main/sdpokemon_emb.safetensors)**.
+    - Place it on it on your `embeddings` folder
+    - Use it by adding `sdpokemon_emb` to your prompt. For example, `<pokemon>`
+    (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('runwayml/stable-diffusion-v1-5', torch_dtype=torch.float16).to('cuda')
+pipeline.load_lora_weights('wannyansports/sdpokemon', weight_name='pytorch_lora_weights.safetensors')
+embedding_path = hf_hub_download(repo_id='wannyansports/sdpokemon', filename='sdpokemon_emb.safetensors', repo_type="model")
+state_dict = load_file(embedding_path)
+pipeline.load_textual_inversion(state_dict["clip_l"], token=[], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
+        
+image = pipeline('<pokemon> with white background').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 `TOK` → use `<s0><s1>` in your prompt 
+
+
+
+## Details
+All [Files & versions](/wannyansports/sdpokemon/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_sd15_advanced.py).
+
+LoRA for the text encoder was enabled. False.
+
+Pivotal tuning was enabled: True.
+
+Special VAE used for training: None.
+

logs/dreambooth-lora-sd-15/1726467319.0785189/events.out.tfevents.1726467319.dc44792b2f5e.1319.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80dc627472d8e92bc186548a8c98f6bc3dc55c37dc682ef30629e1b6509e5de6
+size 3378

logs/dreambooth-lora-sd-15/1726467319.0805333/hparams.yml

@@ -0,0 +1,74 @@
+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: null
+center_crop: false
+checkpointing_steps: 2000
+checkpoints_total_limit: null
+class_data_dir: null
+class_prompt: null
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: huggan/pokemon
+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: <pokemon>
+learning_rate: 1.0
+local_rank: -1
+logging_dir: logs
+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: 1
+num_validation_images: 4
+optimizer: prodigy
+output_dir: sdpokemon
+pretrained_model_name_or_path: emilianJR/epiCRealism
+pretrained_vae_model_name_or_path: null
+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
+rank: 8
+repeats: 1
+report_to: tensorboard
+resolution: 512
+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_dora: false
+validation_epochs: 50
+validation_prompt: <pokemon> with white background
+variant: null
+with_prior_preservation: false

logs/dreambooth-lora-sd-15/events.out.tfevents.1726467319.dc44792b2f5e.1319.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b59242b410459bf6e084acb86b3d85ec4d4e1c99486ed1ccef245143046c642c
+size 2406266

pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d582a1be5ded44158b2832286877fd0448f405c55705afe78d9c930eaa36ca
+size 6414992

sdpokemon.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a5268b4dabe6044c52755ba10f888b2271c1af83458002a035801635e36720
+size 6433712

sdpokemon_emb.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b248c9cb6c8d0ef01a937b30d77d38902ed4c26c39e84c468f36c5a151798208
+size 3152