Update README.md

README.md

@@ -1,34 +1,64 @@
 ---
 tags:
 - text-to-image
+- stable-diffusion
 - lora
 - diffusers
-- template:diffusion-lora
+- image-generation
+- flux
+- safetensors
 widget:
-- text: '-'
+- text: >-
+    ghibli style, a boy and a girl looking out of a window with a cat perched on the window sill. There is a bicycle parked in front of them and a plant with flowers to the right side of the image. The wall behind them is visible in the background.
   output:
-    url: images/example1.png
-- text: '-'
+    url: images/example_1.png
+- text: >-
+    ghibli style, a girl in a green cloak walking alone through an ancient forest, sunlight piercing through towering trees like stained glass, glowing pollen swirling around her boots, a rusted lantern hanging from her wooden staff, shadows of deer spirits flickering between moss-covered stones, muted emerald and gold color palette
   output:
-    url: images/example1.png
+    url: images/example_2.png
+- text: >-
+    ghibli 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
+  output:
+    url: images/example_3.png
 base_model: black-forest-labs/FLUX.1-dev
-instance_prompt: ghibli style
+instance_prompt: >-
+  The background is 4 real photos, and in the middle is a cartoon picture
+  summarizing the real photos
 license: other
 license_name: flux-1-dev-non-commercial-license
 license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
+language:
+- en
+library_name: diffusers
 ---
 # FLUX.1-dev-LoRA-Ghibli
 
-<Gallery />
+This is a Ghibli style LoRA trained on FLUX.1-dev.
 
+<Gallery />
 
 ## Trigger words
 
 You should use `ghibli style` to trigger the image generation.
 
+## 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-Ghibli", weight_name="ghibli_style.safetensors")
+pipe.fuse_lora(lora_scale=1.0)
+pipe.to("cuda")
+
+prompt = "ghibli 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"
 
-## Download model
+image = pipe(prompt, 
+             num_inference_steps=24, 
+             guidance_scale=3.5,
+             width=960, height=1280,
+            ).images[0]
+image.save(f"example.png")
+```
 
-Weights for this model are available in Safetensors format.
 
-[Download](/InstantX/FLUX.1-dev-LoRA-Ghibli/tree/main) them in the Files & versions tab.