End of training

README.md

@@ -9,28 +9,28 @@ tags:
 - template:sd-lora
 widget:
 
-        - text: 'Elandorr riding Gilda'
+        - text: 'DND <s0><s1> Elandorr riding Gilda, scene <s0><s1>'
           output:
             url:
                 "image_0.png"
         
-        - text: 'Elandorr riding Gilda'
+        - text: 'DND <s0><s1> Elandorr riding Gilda, scene <s0><s1>'
           output:
             url:
                 "image_1.png"
         
-        - text: 'Elandorr riding Gilda'
+        - text: 'DND <s0><s1> Elandorr riding Gilda, scene <s0><s1>'
           output:
             url:
                 "image_2.png"
         
-        - text: 'Elandorr riding Gilda'
+        - text: 'DND <s0><s1> Elandorr riding Gilda, scene <s0><s1>'
           output:
             url:
                 "image_3.png"
         
 base_model: stabilityai/stable-diffusion-xl-base-1.0
-instance_prompt: 
+instance_prompt: DND <s0><s1>
 license: openrail++
 ---
 
@@ -51,7 +51,7 @@ license: openrail++
     - On AUTOMATIC1111, load the LoRA by adding `<lora:dnd-SDXL-LoRA:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
 - *Embeddings*: download **[`dnd-SDXL-LoRA_emb.safetensors` here 💾](/weasley24/dnd-SDXL-LoRA/blob/main/dnd-SDXL-LoRA_emb.safetensors)**.
     - Place it on it on your `embeddings` folder
-    - Use it by adding `dnd-SDXL-LoRA_emb` to your prompt. For example, ``
+    - Use it by adding `dnd-SDXL-LoRA_emb` to your prompt. For example, `DND dnd-SDXL-LoRA_emb`
     (you need both the LoRA and the embeddings as they were trained together for this LoRA)
     
 
@@ -67,10 +67,10 @@ pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusi
 pipeline.load_lora_weights('weasley24/dnd-SDXL-LoRA', weight_name='pytorch_lora_weights.safetensors')
 embedding_path = hf_hub_download(repo_id='weasley24/dnd-SDXL-LoRA', filename='dnd-SDXL-LoRA_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)
-pipeline.load_textual_inversion(state_dict["clip_g"], token=[], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
+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('Elandorr riding Gilda').images[0]
+image = pipeline('DND <s0><s1> Elandorr riding Gilda, scene <s0><s1>').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)

dnd-SDXL-LoRA.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52085251a8a6cebcb30ee507fc2db5c05fd67977cd81187d78dbd306c356edb5
+oid sha256:6bb273e6c1922ea5477d119d6d356d136c23db9043984fa4dcf3806ce47c60bc
 size 46698072

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61c2e4c730ac8a284daf72383ff59dfc441c0fb47067042f2b51b4fe57c567a6
+oid sha256:525f6714864de9ff922719de8569ddcdc181f7ef6c95e7ca92a18eeb21d6443c
 size 46615272