正則化係kohya_ss training先咁叫，google正則化應該有
dreambooth應該叫classicification
[ AI Art ] - stable diffusion 討論 分享 02
武吉士
704 回覆
9 Like
8 Dislike
第 1 頁第 2 頁第 3 頁第 4 頁第 5 頁第 6 頁第 7 頁第 8 頁第 9 頁第 10 頁第 11 頁第 12 頁第 13 頁第 14 頁第 15 頁第 16 頁第 17 頁第 18 頁第 19 頁第 20 頁第 21 頁第 22 頁第 23 頁第 24 頁第 25 頁第 26 頁第 27 頁第 28 頁第 29 頁
Let me try try
我明classification data set
不過Lora 都要?
我明classification data set
不過Lora 都要?
依個係bra5?
majicmixRealistic_v5
點解可以咁smoth
pixai到玩左陣 正喎冷門野都gen倒
咁佢每日送10000分倒， 每次gen 4幅512x512 扣200分至1600分左右 ，然後見佢幾秒至幾十秒gen完
咁當自己買張3 4千蚊咁上下價位既gpu
會gen得慢佢幾多／快佢幾多？
咁佢每日送10000分倒， 每次gen 4幅512x512 扣200分至1600分左右 ，然後見佢幾秒至幾十秒gen完
咁當自己買張3 4千蚊咁上下價位既gpu
會gen得慢佢幾多／快佢幾多？
pixai可以任揀埋upload埋lora黎用 真係幾方便，係咪得佢可以咁揀？
巴打點做到D lighting咁自然?
我gen出黎D 圖成日好似打哂燈咁 唔太似一般人影嘅相
利申 新手
我gen出黎D 圖成日好似打哂燈咁 唔太似一般人影嘅相
利申 新手
新手想問問,
其實GEN出黎既圖有冇方法證明佢係用咩MODEL,
證明唔到既話其實果D 商業禁止使用係咪都係廢UP??
其實GEN出黎既圖有冇方法證明佢係用咩MODEL,
證明唔到既話其實果D 商業禁止使用係咪都係廢UP??
what prompt you use?
the only lighting related in prompt to gen this photo was "cinematic light", and "outdoor", it will do the sunny lighting, I didn't do much to control it.
the checkpoint model is "bra v4"
the only lighting related in prompt to gen this photo was "cinematic light", and "outdoor", it will do the sunny lighting, I didn't do much to control it.
the checkpoint model is "bra v4"
I've just changed the checkpoint model and type the two prompts you mentioned, finally made it.
Thx a lot
Thx a lot
quick play with
majicMIX realistic v6近排都玩緊呢個
感覺上好過BRA v5
感覺上好過BRA v5bra 係真人
majic realistic 係2.5D 真人
吾同類別
個人喜好,個個checkpoint 都玩吓
majic realistic 係2.5D 真人
吾同類別
個人喜好,個個checkpoint 都玩吓
infinite image browsing so nice and useful.https://github.com/zanllp/sd-webui-infinite-image-browsing
唔知點解我用V6會爛圖，但係v5冇事
BTW我都覺得majic超越咗chillout同BRA， 不過好似衣物材質嘅種類冇chill咁多。
BTW我都覺得majic超越咗chillout同BRA， 不過好似衣物材質嘅種類冇chill咁多。
use too many lora? 