Download
1 variant available
14,0460 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9,0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
Aug 15, 2025
Wan Video 2.2 T2V-A14B
What's New in v2.3: This is a focused update aimed at enhancing prompt control and aesthetic consistency. All existing features of V2 remain, now with greater precision.
Superior Prompt Adherence: The entire dataset has been meticulously re-captioned using a more natural and detailed language structure. The LoRA now understands your prompts with higher accuracy.
Refined Aesthetics: We've curated the dataset to reduce the frequency of unwanted elements like excessive finger rings and belly piercings.
Enhanced Cohesion: Further dataset cleanup has improved overall image quality and consistency, reinforcing the hyper-realistic style.
Show more

1.6K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
3.5K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
60.4K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
License:
Apache 2.0How to Use
This is a style LoRA, designed to be the base layer of your LoRA stack. It creates the foundational aesthetic of realism, upon which you can add character or concept LoRAs.
Note: The included ZIP archive contains both the high-noise and low-noise LoRA variants, along with our recommended ComfyUI workflows.
Trigger Word:
InstacamRecommended Strength:
1.0. Start here and adjust in small increments.
I would also like to thank Danrisi, who originally taught us how to train LoRAs and helped make our work possible.
