I trained new lora with the same old dataset with new learning rate,text lr , with the help of adafactor, the result is surprise, big changes are
1. more colorful
2. can regconize stuff better
3. line is kinda thin now i guess
4.many variants for 1 character (time to gacha)
In my opinion, this one will have more quality results.
Input
Per image generation will cost 0.0047$
For premium plan image generation will cost 0.00$ i.e Free.
Output
Unknown content type
Related Models
Discover similar models you might be interested in
Ninja Yagyu (Senran Kagura: New Link) - v1.0
LoRA Peace Sign - v0.3
Watermelon Print Bikini | Attire - v1.0
![[Clothing] Hair Bow Variation / - top_of_head-v1.0](https://images.modelslab.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/e9f2daf4-327d-4f90-81d4-7a18dd736708/width=1024/3557820.jpeg)
[Clothing] Hair Bow Variation / - top_of_head-v1.0
Aiko Rivera - v1.0
TestModelDino308gt4 - v1.0
Belle (Final Fantasy Crystal Chronicles: Crystal Bearers - v1.0
qrcode-v8
Nene Kusanagi - v3.0
Yuuta Kadowaki | Otonari no Tenshi-sama ni Itsunomanika Dame Ningen ni Sareteita Ken / The Angel Nex
Serenity - v2.1 SafeTensors
Miyagishi Yuuki (Hentai: Discipline: Record of a Crusade) NoobAI / IL / Pony / SD1.5 - SD1.5 animefu