End of training

README.md

@@ -9,28 +9,28 @@ tags:
 - template:sd-lora
 widget:
 
-        - text: 'a TOK icon of an astronaut riding a horse, in the style of TOK'
+        - text: 'a TOK word of mychar, white background, in the style of TOK'
           output:
             url:
                 "image_0.png"
         
-        - text: 'a TOK icon of an astronaut riding a horse, in the style of TOK'
+        - text: 'a TOK word of mychar, white background, in the style of TOK'
           output:
             url:
                 "image_1.png"
         
-        - text: 'a TOK icon of an astronaut riding a horse, in the style of TOK'
+        - text: 'a TOK word of mychar, white background, in the style of TOK'
           output:
             url:
                 "image_2.png"
         
-        - text: 'a TOK icon of an astronaut riding a horse, in the style of TOK'
+        - text: 'a TOK word of mychar, white background, in the style of TOK'
           output:
             url:
                 "image_3.png"
         
 base_model: stabilityai/stable-diffusion-xl-base-1.0
-instance_prompt: 3d icon in the style of TOK
+instance_prompt: character in the style of TOK
 license: openrail++
 ---
 
@@ -60,14 +60,14 @@ import torch
 pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
 pipeline.load_lora_weights('nicolaus-huang/3d-icon-SDXL-LoRA-eng', weight_name='pytorch_lora_weights.safetensors')
 
-image = pipeline('a TOK icon of an astronaut riding a horse, in the style of TOK').images[0]
+image = pipeline('a TOK word of mychar, white background, in the style of TOK').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 3d icon in the style of TOK to trigger the image generation.
+You should use character in the style of TOK to trigger the image generation.
 
 ## Details
 All [Files & versions](/nicolaus-huang/3d-icon-SDXL-LoRA-eng/tree/main).