模型/iPhone Photo [FLUX•SD3.5L] (Realism booster) - v1 final

iPhone Photo [FLUX•SD3.5L] (Realism booster) - v1 final

|
7/3/2025
|
11:34:55 AM
| Discussion

推薦提示詞

iphone photo,iph0ne

推薦參數

samplers

Euler

steps

6 - 8

cfg

3.5

提示

Adding trigger words like "iphone photo" sharpens the background and improves realism.

For Flux model, use trigger "iphone photo"; for SD3.5 Large use "iph0ne" with lower weight around 0.5.

Trained with Ostris's ai-toolkit available at Github.

版本亮點

Retrained with different parameters and dataset cleanup of problematic images.

Same as before, trigger word is "iphone photo" but it will work without it. It may help to increase the effect but is not necessary.

Doesn't require a trigger word, but adding them to the prompt will help sharpen the background and make it look like an actual iphone photo, otherwise it serves as an all purpose realism enhancer and will make all images more natural.

For Flux, the trigger is "iphone photo".
For SD3.5 Large it's "iph0ne", try lower weight around 0.5.. first attempt at sd3.5, it might be bad.

Trained with Ostris's ai-toolkit: Github page

SD3.5 Large V2 Test version comparison - FLUX V1 vs V2 comparisons below

FLUX
V1 is iPhone Photo 6-2000 /// V2 is iPhone Photo 7-15000

貢獻者

上一個
MoriiMee Gothic Niji | LoRA Style - V1 FLUX
下一個
J_Anime - first approach

模型詳情

模型類型

LORA

基礎模型

Flux.1 D

模型版本

v1 final

模型雜湊值

540c49c9f4

訓練詞彙

iphone photo

創作者

討論

log in以發表評論。