End of training

README.md

@@ -8,28 +8,28 @@ tags:
 - template:sd-lora
 widget:
 
-        - text: 'a TOK woman with pink hair at a party'
+        - text: 'a <s0><s1> woman with pink hair at a party'
           output:
             url:
                 "image_0.png"
         
-        - text: 'a TOK woman with pink hair at a party'
+        - text: 'a <s0><s1> woman with pink hair at a party'
           output:
             url:
                 "image_1.png"
         
-        - text: 'a TOK woman with pink hair at a party'
+        - text: 'a <s0><s1> woman with pink hair at a party'
           output:
             url:
                 "image_2.png"
         
-        - text: 'a TOK woman with pink hair at a party'
+        - text: 'a <s0><s1> woman with pink hair at a party'
           output:
             url:
                 "image_3.png"
         
 base_model: stabilityai/stable-diffusion-xl-base-1.0
-instance_prompt: photo of a TOK woman
+instance_prompt: photo of a <s0><s1> woman
 license: openrail++
 ---
 
@@ -48,25 +48,39 @@ license: openrail++
 - **LoRA**: download **[`linoy_lora_pivotal.safetensors` here 💾](/linoyts/linoy_lora_pivotal/blob/main/linoy_lora_pivotal.safetensors)**.
     - Place it on your `models/Lora` folder.
     - On AUTOMATIC1111, load the LoRA by adding `<lora:linoy_lora_pivotal:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
-
+- *Embeddings*: download **[`linoy_lora_pivotal_emb.safetensors` here 💾](/linoyts/linoy_lora_pivotal/blob/main/linoy_lora_pivotal_emb.safetensors)**.
+    - Place it on it on your `embeddings` folder
+    - Use it by adding `linoy_lora_pivotal_emb` to your prompt. For example, `photo of a linoy_lora_pivotal_emb woman`
+    (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('linoyts/linoy_lora_pivotal', weight_name='pytorch_lora_weights.safetensors')
-
-image = pipeline('a TOK woman with pink hair at a party').images[0]
+embedding_path = hf_hub_download(repo_id='linoyts/linoy_lora_pivotal', filename='linoy_lora_pivotal_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 <s0><s1> woman with pink hair at a party').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 photo of a TOK woman to trigger the image generation.
+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](/linoyts/linoy_lora_pivotal/tree/main).
@@ -75,7 +89,7 @@ The weights were trained using [🧨 diffusers Advanced Dreambooth Training Scri
 
 LoRA for the text encoder was enabled. False.
 
-Pivotal tuning was enabled: False.
+Pivotal tuning was enabled: True.
 
 Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
 

linoy_lora_pivotal.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bfceb3f47e112cf7791ce2c283c94b328a0d82dea45d1642014871c2ed5e0b9
+oid sha256:970f4dcbf8196890378b2ce26e10d45e2af385cae42367b67cd39121494fc436
 size 186046568

linoy_lora_pivotal_emb.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f583cf8b9f5743cc946d137feba3034f2041abec97d89957f6b8c8b4efe96698
+oid sha256:2e78a5e9dcaa7b028dbf6976c01fff42113cd948e9d77ed5db137a5f640b997c
 size 16536

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e6256955b818881a1fcfb27e335cad7e685b859897a6d0d6ec6d4b8f59e31fb
+oid sha256:5d3b1a1f84d3ecb559ca62a4db2c3dbedb3bed763c1a6d6cff4ca0a4cba85bb5
 size 185963768