Notes:
The LoRA sometime gives deformed anatomy, especially feet and sometime hand, just change the prompt or the seed to get better result
Since the pose a little bit tricky, I always use simple prompt to avoid weird result
The LoRA trained for Flux1 Dev, please read this before use the LoRA:
Guidance: 3.5
Sampler/Scheduler: Euler/Simple (feel free to experiment)
Steps: 20-40
Size: 896x1152 (3:4)
LoRA weight: 1.0 (feel free to experiment)
Trigger words: layingdownmermaidposeselfie
Notes: Explain what is the background
Anyway, feel free to do some experimentation and I can't wait to see your results in the gallery, please share it :)
How was the dataset captioned?
I use some short sentence, some long sentence, and some single word.
I combine chatbot and manual work.
If you have feedback feel free to tell me and I will improve it in the next version.
Description
Trained on 30 images of a person laying down doing mermaid pose selfie
FAQ
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.