End of training

README.md

@@ -1,4 +1,5 @@
 ---
+
 tags:
 - stable-diffusion-xl
 - stable-diffusion-xl-diffusers
@@ -7,30 +8,31 @@ tags:
 - diffusers
 - lora
 - template:sd-lora
+
 widget:
 
-        - text: 'watercolor painting of a <s0><s1> woman with pink hair in New York'
+        - text: 'a TOK emoji dressed as an easter bunny'
           output:
             url:
                 "image_0.png"
         
-        - text: 'watercolor painting of a <s0><s1> woman with pink hair in New York'
+        - text: 'a TOK emoji dressed as an easter bunny'
           output:
             url:
                 "image_1.png"
         
-        - text: 'watercolor painting of a <s0><s1> woman with pink hair in New York'
+        - text: 'a TOK emoji dressed as an easter bunny'
           output:
             url:
                 "image_2.png"
         
-        - text: 'watercolor painting of a <s0><s1> woman with pink hair in New York'
+        - text: 'a TOK emoji dressed as an easter bunny'
           output:
             url:
                 "image_3.png"
         
 base_model: stabilityai/stable-diffusion-xl-base-1.0
-instance_prompt: a <s0><s1> woman
+instance_prompt: a TOK emoji
 license: openrail++
 ---
 
@@ -49,39 +51,25 @@ license: openrail++
 - **LoRA**: download **[`huggy_lora_v4.safetensors` here 💾](/linoyts/huggy_lora_v4/blob/main/huggy_lora_v4.safetensors)**.
     - Place it on your `models/Lora` folder.
     - On AUTOMATIC1111, load the LoRA by adding `<lora:huggy_lora_v4:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
-- *Embeddings*: download **[`huggy_lora_v4_emb.safetensors` here 💾](/linoyts/huggy_lora_v4/blob/main/huggy_lora_v4_emb.safetensors)**.
-    - Place it on it on your `embeddings` folder
-    - Use it by adding `huggy_lora_v4_emb` to your prompt. For example, `a huggy_lora_v4_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/huggy_lora_v4', weight_name='pytorch_lora_weights.safetensors')
-embedding_path = hf_hub_download(repo_id='linoyts/huggy_lora_v4', filename='huggy_lora_v4_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('watercolor painting of a <s0><s1> woman with pink hair in New York').images[0]
+
+image = pipeline('a TOK emoji dressed as an easter bunny').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 
-
-
+You should use a TOK emoji to trigger the image generation.
 
 ## Details
 All [Files & versions](/linoyts/huggy_lora_v4/tree/main).
@@ -90,7 +78,7 @@ The weights were trained using [🧨 diffusers Advanced Dreambooth Training Scri
 
 LoRA for the text encoder was enabled. False.
 
-Pivotal tuning was enabled: True.
+Pivotal tuning was enabled: False.
 
 Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
 

huggy_lora_v4.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b35b9bbf7781e4fef726facb8cced42b47e9b3f1a47f5026c01924c5dffc41f
-size 186046568
+oid sha256:0a35100f826cf351f6d9c3ec1a059b533780f8660aa0908ea114161706336eb9
+size 46698072

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e13e9f895e2e8eb23aa54e65521155915e46779afc6c3b08f302abc7123799b8
-size 185963768
+oid sha256:825e9ded2d46541eb39522fed28b21a123d28bbc24098a1c4271f9231ceb3f89
+size 46615272