End of training

README.md

@@ -8,28 +8,28 @@ tags:
 - template:sd-lora
 widget:
 
-        - text: 'a TOK ad for lego with a T2K emoji'
+        - text: 'a <s0><s1> ad for lego with a <s2><s3> emoji'
           output:
             url:
                 "image_0.png"
         
-        - text: 'a TOK ad for lego with a T2K emoji'
+        - text: 'a <s0><s1> ad for lego with a <s2><s3> emoji'
           output:
             url:
                 "image_1.png"
         
-        - text: 'a TOK ad for lego with a T2K emoji'
+        - text: 'a <s0><s1> ad for lego with a <s2><s3> emoji'
           output:
             url:
                 "image_2.png"
         
-        - text: 'a TOK ad for lego with a T2K emoji'
+        - text: 'a <s0><s1> ad for lego with a <s2><s3> emoji'
           output:
             url:
                 "image_3.png"
         
 base_model: stabilityai/stable-diffusion-xl-base-1.0
-instance_prompt: a TOK ad for lego with a T2K emoji
+instance_prompt: a <s0><s1> ad for lego with a <s2><s3> emoji
 license: openrail++
 ---
 
@@ -48,34 +48,51 @@ license: openrail++
 - **LoRA**: download **[`ad_huggy.safetensors` here 💾](/linoyts/ad_huggy/blob/main/ad_huggy.safetensors)**.
     - Place it on your `models/Lora` folder.
     - On AUTOMATIC1111, load the LoRA by adding `<lora:ad_huggy:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
-
+- *Embeddings*: download **[`ad_huggy_emb.safetensors` here 💾](/linoyts/ad_huggy/blob/main/ad_huggy_emb.safetensors)**.
+    - Place it on it on your `embeddings` folder
+    - Use it by adding `ad_huggy_emb` to your prompt. For example, `a ad_huggy_emb ad for lego with a  emoji`
+    (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/ad_huggy', weight_name='pytorch_lora_weights.safetensors')
-
-image = pipeline('a TOK ad for lego with a T2K emoji').images[0]
+embedding_path = hf_hub_download(repo_id='linoyts/ad_huggy', filename='ad_huggy_emb.safetensors', repo_type="model")
+state_dict = load_file(embedding_path)
+pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>", "<s2>", "<s3>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
+pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>", "<s2>", "<s3>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
+        
+image = pipeline('a <s0><s1> ad for lego with a <s2><s3> emoji').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 a TOK ad for lego with a T2K emoji 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 
+
+
+to trigger concept `T2K` → use `<s2><s3>` in your prompt 
+
+
 
 ## Details
 All [Files & versions](/linoyts/ad_huggy/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. True.
+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.
 

ad_huggy.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5771c0256bacd30d9083a50e07c68df2894980ef7d4b7c99568ed848fd1f5c71
-size 237421752
+oid sha256:ac9a344e053c8a01a8ac40134260844c912fc07c3e028f2a5d1579c1711571a6
+size 186046568

ad_huggy_emb.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a7251dc71b0c2caee9ec07a3fae6ac30ad09fc1f5341308adffbbd09f027b0
+size 32920

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e437d6271e20d8ed9ab51282460f35f28f36974277560b79c06afc17ab89f409
-size 237400944
+oid sha256:dfc3974ab283e79969db2679de2ba3052abcbcddbc6314a79d936f35222c9553
+size 185963768