Update README.md

README.md

@@ -1,9 +1,12 @@
 ---
 tags:
 - text-to-image
+- stable-diffusion
 - lora
 - diffusers
-- template:diffusion-lora
+- image-generation
+- flux
+- safetensors
 widget:
 - text: >-
     Makoto Shinkai style, a boy and a girl looking out of a window with a cat
@@ -35,6 +38,8 @@ license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICE
 ---
 # FLUX.1-dev-LoRA-Makoto-Shinkai
 
+This is a Makoto Shinkai style LoRA trained on FLUX.1-dev.
+
 <Gallery />
 
 
@@ -43,8 +48,23 @@ license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICE
 You should use `Makoto Shinkai style` to trigger the image generation.
 
 
-## Download model
+## Inference
+```python
+import torch
+from diffusers import FluxPipeline
+
+pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
+pipe.load_lora_weights("InstantX/FLUX.1-dev-LoRA-Makoto-Shinkai", weight_name="Makoto_Shinkai_style.safetensors")
+pipe.fuse_lora(lora_scale=1.0)
+pipe.to("cuda")
+
+prompt = "Makoto Shinkai style, a shepherd boy floating on a wooly cloud-whale, holding a glowing dandelion staff to guide sheep-shaped cumulus, miniature storm clouds grazing nearby, his patched jacket flapping in high-altitude winds, aurora-like ribbons in peach and lavender stretching across the sky"
 
-Weights for this model are available in Safetensors format.
+image = pipe(prompt, 
+             num_inference_steps=24, 
+             guidance_scale=3.5,
+             width=960, height=1280,
+            ).images[0]
+image.save(f"example.png")
+```
 
-[Download](/InstantX/FLUX.1-dev-LoRA-Makoto-Shinkai/tree/main) them in the Files & versions tab.