Downloads · 30 days
189
13% of all-time downloads
mh3-morphing-helper
kabachuha/mh3-morphing-helper
mh3-morphing-helper is a image-text-to-video model from kabachuha. Use it for the image-text-to-video task on the model card, and read the license before you ship it in a product. It is set up for diffusers. The card lists the license as other.
All-time downloads
1.4K
Public
Repo size
624 MB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors596 MB · 96%
At a glance
- Task
- Image-Text-to-Video
- Library
- diffusers
- License
- other
- Access
- Public
- Created
- Aug 6, 2026
- Updated
- Aug 12, 2026
- SHA
- 4129e73d
Try a prompt
Base models
Model card
From the Hugging Face model README
H3 Morphing Helper
<Gallery />Model description
aka Claymation Transformation V2
In my experience, H3 doesn't very well interact with object morphing into each other out-of-the-box.
This LoRA, fine-tuned on the transfomation-rich plasticine/claymation cartoon "Last Year Snow was Falling" (LYS) steers the model towards that "plasticine"-melting feel where the object is seemingly crushed and almost manually reshaped into a new object.
This LoRA is preliminary (or maybe not), because it trained for ~9 hours for 84 epochs and then it triggered the circuit breaker and I wasn't able to resume it properly, so maybe more train is needed, but it already works good in my opinion. If it's good, I will publish it to my CivitAI.
For now, enjoy!
Example prompt:
The LYS-style transformation video begins with a cup of coffee. Then suddenly the cup of coffee plasticine-transforms into a realistic parrot.
The two necessary trigger words are: "LYS-style", "plasticine-transforms".
Trigger words
You should use LYS-style to trigger the image generation.
You should use plasticine-transforms to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Task
- Image-Text-to-Video
- Library
- diffusers
- License
- other
- Languages
- en
- Wavespeed
- live
- Created
- Aug 6, 2026
- Updated
- Aug 12, 2026