End of training

README.md

@@ -0,0 +1,76 @@
+---
+tags:
+- stable-diffusion-xl
+- stable-diffusion-xl-diffusers
+- text-to-image
+- diffusers
+- lora
+- template:sd-lora
+widget:
+
+        - text: 'a phot in the fashion style of <s0>'
+        
+instance_prompt: a phot in the fashion style of <s0>
+license: openrail++
+---
+
+# SDXL LoRA DreamBooth - armhebb/65995e622d50edfb3ead
+
+<Gallery />
+
+## Model description
+
+### These are armhebb/65995e622d50edfb3ead LoRA adaption weights.
+
+## Download model
+
+### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
+
+- **LoRA**: download **[`/korean_sample_checkpoint.safetensors` here 💾](/armhebb/65995e622d50edfb3ead/blob/main//korean_sample_checkpoint.safetensors)**.
+    - Place it on your `models/Lora` folder.
+    - On AUTOMATIC1111, load the LoRA by adding `<lora:/korean_sample_checkpoint:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
+- *Embeddings*: download **[`/korean_sample_checkpoint_emb.safetensors` here 💾](/armhebb/65995e622d50edfb3ead/blob/main//korean_sample_checkpoint_emb.safetensors)**.
+    - Place it on it on your `embeddings` folder
+    - Use it by adding `/korean_sample_checkpoint_emb` to your prompt. For example, `a phot in the fashion style of /korean_sample_checkpoint_emb`
+    (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('armhebb/65995e622d50edfb3ead', weight_name='pytorch_lora_weights.safetensors')
+embedding_path = hf_hub_download(repo_id='armhebb/65995e622d50edfb3ead', filename='/korean_sample_checkpoint_emb.safetensors' repo_type="model")
+state_dict = load_file(embedding_path)
+pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
+pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
+        
+image = pipeline('a phot in the fashion style of <s0>').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 `<GFJ>` → use `<s0>` in your prompt 
+
+
+
+## Details
+All [Files & versions](/armhebb/65995e622d50edfb3ead/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: None.
+

korean_sample_checkpoint.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0a2f78840c65ec96e6212ff6e531fc5945ace88e9f5e264bf780f8e7d94f3b
+size 186046568

korean_sample_checkpoint_emb.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f323306f9e3e1af74f180c92b59de077760a009ced3a5e118fabfeac34926ba
+size 4240

pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb86255735e5a92357c6e7e5bba300ea815f50689bbc9e174fdf25f045131c5
+size 185963768