Upload README.md with huggingface_hub

README.md

@@ -1,3 +1,119 @@
----
-license: mit
----
+---
+license: apache-2.0
+language:
+- en
+- zh
+tags:
+- image-to-video
+- lora
+- replicate
+- text-to-video
+- video
+- video-generation
+base_model: "Wan-AI/Wan2.1-I2V-14B-Diffusers"
+pipeline_tag: image-to-video
+# widget:
+#   - text: >-
+#       prompt
+#     output:
+#       url: https://...
+instance_prompt: SQUISH-IT
+---
+
+# Squish Pika Lora
+
+<Gallery />
+
+## About this LoRA
+
+This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the Wan 14B Image-to-Video model.
+
+It can be used with diffusers or ComfyUI, and can be loaded against the Wan 14B models.
+
+It was trained on [Replicate](https://replicate.com/) with 10 steps at a learning rate of 2e-05 and LoRA rank of 32.
+
+
+## Trigger word
+
+You should use `SQUISH-IT` to trigger the video generation.
+
+
+## Use this LoRA
+
+Replicate has a collection of Wan models that are optimised for speed and cost. They can also be used with this LoRA:
+
+- https://replicate.com/collections/wan-video
+- https://replicate.com/fofr/wan-with-lora
+
+### Run this LoRA with an API using Replicate
+
+```py
+import replicate
+
+input = {
+    "prompt": "SQUISH-IT",
+    "lora_url": "https://huggingface.co/zsxkib/squish-pika-lora/resolve/main/wan-14b-i2v-squish-it-lora.safetensors"
+}
+
+output = replicate.run(
+    "fofr/wan-with-lora:latest",
+    model="14B",
+    input=input
+)
+for index, item in enumerate(output):
+    with open(f"output_{index}.mp4", "wb") as file:
+        file.write(item.read())
+```
+
+### Using with Diffusers
+
+```py
+import torch
+from diffusers.utils import export_to_video
+from diffusers import WanVidAdapter, WanVid
+
+# Load base model
+base_model = WanVid.from_pretrained("Wan-AI/Wan2.1-I2V-14B-Diffusers", torch_dtype=torch.float16)
+
+# Load and apply LoRA adapter
+adapter = WanVidAdapter.from_pretrained("zsxkib/squish-pika-lora")
+base_model.load_adapter(adapter)
+
+# Generate video
+prompt = "SQUISH-IT"
+negative_prompt = "blurry, low quality, low resolution"
+
+# Generate video frames
+from PIL import Image
+
+# Load input image
+image = Image.open("path/to/your/image.jpg").convert("RGB")
+
+# Generate video from image
+frames = base_model.image_to_video(
+    image=image,
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    num_inference_steps=30,
+    guidance_scale=5.0,
+    fps=16,
+    num_frames=32,
+).frames[0]
+
+# Save as video
+video_path = "output.mp4"
+export_to_video(frames, video_path, fps=16)
+print(f"Video saved to: {video_path}")
+```
+
+
+## Training details
+
+- Steps: 10
+- Learning rate: 2e-05
+- LoRA rank: 32
+
+
+## Contribute your own examples
+
+You can use the [community tab](https://huggingface.co/zsxkib/squish-pika-lora/discussions) to add videos that show off what you've made with this LoRA.