Downloads · 30 days
0
Krea2-H3-Style-Lora
TenStrip/Krea2-H3-Style-Lora
Krea2-H3-Style-Lora is a image-text-to-video model from TenStrip. 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.
This is a lora for the video h3 model, using krea2 attn k/v. Only effective for pure T2V generations as a lora.
Access
Public
Updated Aug 8, 2026
Repo size
1.4 GB
Likes
19
Trending 1
Repo makeup
Click a slice to open those files.
.safetensors1.4 GB · 100%
At a glance
- Task
- Image-Text-to-Video
- License
- other
- Access
- Public
- Created
- Aug 8, 2026
- Updated
- Aug 8, 2026
- SHA
- 6e80e180
Base models
Model card
From the Hugging Face model README
This is a lora for the video h3 model, using krea2 attn k/v. Only effective for pure T2V generations as a lora.
This is extraction result from Krea2 branch of my attn graft experiments. At rank 512 the lora only captures 52% of the SLERP orthagonal delta inside the generated Krea2 full model version for test1 and rank 128 is only 24% (too negligible), those degree shifts are hard extraction targets, but it produces a large shift in T2V usage and visual style. All experimental. Refer to Eros Max page for exact methodology of how cross-model attn grafting works inside H3 model.
- Task
- Image-Text-to-Video
- License
- other
- Created
- Aug 8, 2026
- Updated
- Aug 8, 2026