Update README.md

README.md

@@ -1,14 +1,25 @@
 ---
 tags:
 - text-to-image
+- stable-diffusion
 - lora
 - diffusers
-- template:diffusion-lora
+- image-generation
+- flux
+- safetensors
 widget:
-- output:
-    url: images/image (3).jpg
-  text: convert to a pixel art style
-base_model: ''
+- text: >-
+    Convert to a flat cartoon style while keeping the subject unchanged
+  output:
+    url: images/example1.png
+- text: >-
+    Convert to a flat cartoon style while keeping the subject unchanged
+  output:
+    url: images/example2.png
+- text: Convert to a flat cartoon style while keeping the subject unchanged
+  output:
+    url: images/example3.png
+base_model: black-forest-labs/FLUX.1-Kontext-dev
 instance_prompt: A pixel art style
 license: other
 license_name: flux-1-dev-non-commercial-license
@@ -17,15 +28,39 @@ license_link: >-
 ---
 # FLUX.1-Kontext-dev-LoRA-Pixel-Style
 
-<Gallery />
+This is a pixel style LoRA trained on FLUX.1-Kontext-dev by [zooey](https://huggingface.co/zooeyy).
 
+## Showcases
+<Gallery />
 
 ## Trigger words
 
 You should use `A pixel art style` to trigger the image generation.
 
 
-## Download model
+## Inference
+
+```python
+import torch
+from diffusers import FluxKontextPipeline
+from diffusers.utils import load_image
+
+pipe = FluxKontextPipeline.from_pretrained("black-forest-labs/FLUX.1-Kontext-dev", torch_dtype=torch.bfloat16)
+pipe.load_lora_weights("Shakker-Labs/FLUX.1-Kontext-dev-LoRA-Pixel-Style", weight_name="FLUX-kontext-lora-pixel-style.safetensors")
+pipe.fuse_lora(lora_scale=1.0)
+pipe.to("cuda")
+
+input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
+prompt = "Convert to a pixel art style"
 
+image = pipe(
+    image=input_image,
+    prompt=prompt, 
+    num_inference_steps=24, 
+    guidance_scale=2.5,
+).images[0]
+image.save(f"example.png")
+```
 
-[Download](/Shakker-Labs/FLUX.1-Kontext-dev-LoRA-Pixel-Style/tree/main) them in the Files & versions tab.
+## Acknowledgements
+This model is trained by our copyrighted users [zooey](https://huggingface.co/zooeyy). We release this model under permissions. The model follows [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).