Downloads · 30 days
0
Minimax-h3_Singularity-Lora
EllipsesMark/Minimax-h3_Singularity-Lora
Minimax-h3_Singularity-Lora is a image-text-to-video model from EllipsesMark. Use it for the image-text-to-video task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Extract from base hybrid pruned against https://huggingface.co/WarmBloodAban/Minimax-h3Singularity/tree/main with spectral dampening. Still has a very intense effect and may capture unintended ref/fl signatures that d…
Access
Public
Updated Sep 8, 2026
Repo size
1.9 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors1.9 GB · 100%
At a glance
- Task
- Image-Text-to-Video
- License
- other
- Access
- Public
- Created
- Sep 8, 2026
- Updated
- Sep 8, 2026
- SHA
- ed8e44d3
Base models
Model card
From the Hugging Face model README
Extract from base hybrid pruned against https://huggingface.co/WarmBloodAban/Minimax-h3_Singularity/tree/main with spectral dampening. Still has a very intense effect and may capture unintended ref/fl signatures that double down and can cause drift at high strengths. Use 0.5 or lower to taste.
They should release their lora officially, idk why it's locked inside a quantized checkpoint I would've started with releasing the lora for wider usage. I'll delete and defer to that when they do.
- Task
- Image-Text-to-Video
- License
- other
- Created
- Sep 8, 2026
- Updated
- Sep 8, 2026