ZXTOPOWER/Wan2.2 - Korean Women
I occasionally get asked how I build LoRA training datasets, so I customized this tool based on a project by @tazmannner379 (thanks for sharing) . It generates captions from images or videos using a VL model and integrates with ComfyUI for visual feedback. https://github.com/zxtopower-tech/LoRA-Caption-Assistant Uses paid APIs (Google or OpenAI-compatible). Local models require Ollama or LM Studio. 2025-09-06 I'm finally releasing Seoullina v2.1 . This was s'posed to be a small, quick fix, but it ended up getting delayed as a few things came up. TBH, I'm not entirely happy with how it turned o
| Author / organization | ZXTOPOWER |
|---|---|
| Downloads | 13.5K (as reported by Civitai) |
| Likes | 898 |
| Task | text-to-image |
| Created | 6 September 2025 |
| Last updated at source | — |
Popularity, last 2 days
13,529 now (+2 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.
More from ZXTOPOWER
Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 16 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.