Detail
Rekomendasi
White Shoes v1.0
Vans Look Alike Low-Top White Shoes

Vans Look Alike Low-Top White Shoes

0
1
11
#Clothing
#shoes
#Illustrious

I wanted to ???????? shoes in for more consistent looks. Got to say, never realise how difficult it is to get consistent shoes. The Lora was trained using 51 images of a pair of Vans look alike shoes, however, depending on which Illustrious checkpoint you use, the results vary, but you still get similar shoes per output. The one checkpoint that gave me the best result so far is Fabricated XL.

Currently, the Lora works best using the following settings:

Trigger word: CHRNVWhitelowtop

Additional / useful prompts (positive): white low-top sneaker, eyelets, laces

(*if you want to add more details, try eyelets, laces)

Additional / useful prompts (negative): So far, I didn't use any specific ones for the shoes.

Weightage: 0.5 ~ 1

(This is the hardest part, I trained only shoes without any other subjects, humans, hands, feet etc., to ensure that the trained model would focus on the shoes, nevertheless, some checkpoints give varied output from weightage 0.5 (sometimes 0.4) ~ 1)

Checkpoint Tested: Fabricated XL, WAI-????-illustrious-SDXL, JANKU v5 ???? Trained + NoobAI + RouWei Illustrious XL, Nova Orange XL

(it's the only one I've used so far to test the outputs)

Weaknesses

Overall, I've been able to get similar results of the white shoes I want across the images I've been able to generate, though I can't seem to get an exact look alike. Do tailor or adjust the prompts to see if you can get the kind of look that you want, especially when trying to generate subjects with a white pair of shoes. I hit a wall as to trying to create a better Lora since my previous shoes Lora have also not produced decent results.

If you have any feedback or suggestions, please let me know. You can download the training model and the pictures to see my workflow.

Conclusion

I'm quite happy with the decent outputs I get, but more improvement is certainly needed. I'll continue to find ways hopefully, and... try to get better. In the meantime, I'll try to polish my skills before the next set of Lora.

I hope you guys will have a good time generating!

Lihat terjemahan

Rating dan Ulasan

-- /5
0 rating

Belum menerima penilaian atau komentar yang cukup

no-data
Tidak Ada Data
avatar
Berbicara dengan model
Pengumuman
2025-09-08
Memposting model
2025-09-08
Perbarui informasi model
Detail model
Jenis
LORA
Waktu publikasi
2025-09-08
Model Dasar
Illustrious
Kata Pemicu
CHRNVWhitelowtop
Salin
Perkenalan versi

Initial version

Cakupan Lisensi
Model Source: civitai

1. Hak untuk model yang diposting ulang adalah milik pembuat aslinya.

2. Pencipta asli yang ingin mengklaim model harap hubungi staf SeaArt AI melalui saluran resmi. Klik untuk mengklaim

Cakupan Lisensi Penciptaan
Gambar Online
Melakukan Penggabungan
Izinkan Unduhan
Lisensi Komersial
Gambar yang dihasilkan dapat dijual atau digunakan untuk tujuan komersial
Izinkan model dijual kembali atau dijual setelah penggabungan
QR Code
Unduh SeaArt App
Lanjutkan perjalanan kreasi AI Anda di perangkat mobile