Downloads · 30 days
15
6% of all-time downloads
mochi-lora-melty
lucataco/mochi-lora-melty
mochi-lora-melty is a text-to-video model from lucataco. Use it when you need video from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
234
Public
Repo size
76.1 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors76.1 MB · 100%
At a glance
- Task
- Text-to-Video
- Library
- diffusers
- License
- apache-2.0
- Access
- Public
- Created
- Dec 12, 2024
- Updated
- Dec 13, 2024
- SHA
- 20ceac62
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
Mochi-1 Preview LoRA Finetune
This is a LoRA fine-tune of the Mochi-1 preview model. The model was trained using custom training data.
<Gallery />Usage
from diffusers import MochiPipeline
from diffusers.utils import export_to_video
import torch
pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview")
pipe.load_lora_weights("lucataco/mochi-lora-melty")
pipe.enable_model_cpu_offload()
video = pipe(
prompt="your prompt here",
guidance_scale=6.0,
num_inference_steps=64,
height=480,
width=848,
max_sequence_length=256,
).frames[0]
export_to_video(video, "output.mp4", fps=30)
Training details
Trained on Replicate using: lucataco/mochi-1-lora-trainer
- Task
- Text-to-Video
- Library
- diffusers
- License
- apache-2.0
- Created
- Dec 12, 2024
- Updated
- Dec 13, 2024