Yoshitaka Amano Style LoRA - v2_offset
Verwandte Schlüsselwörter & Tags
Empfohlene Prompts
amano yoshitaka
amano yoshitaka, 1girl, solo
Empfohlene Negative Prompts
(painting by bad-artist-anime:0.9), (painting by bad-artist:0.9), text, error, blurry, cropped, watermark, worst quality, jpeg artifacts, low quality, normal quality, signature, username, artist name, (worst quality, low quality:1.4), bad anatomy
Empfohlene Parameter
samplers
steps
cfg
resolution
other models
Empfohlene Hires (Hochauflösungs-) Parameter
upscaler
upscale
steps
denoising strength
Tipps
Use around 0.9 weight for v1 versions of the LoRA.
For v2 versions, use weight over 1, with 1.25 recommended to capture distinctive shapes.
Lower weights emphasize coloration and pencil style but reduce distinctive shapes.
The LoRA trigger word is 'amano yoshitaka'.
Works well with embeddings and other LoRA nets for character customization.
In auto1111, make sure to update the web UI and correctly place the LoRA file in stable-diffusion-webui/models/lora.
Adjust LoRA weight in auto1111 to avoid default weight of 1, which is usually too high.
Ersteller-Sponsoren
Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
Yoshitaka Amano style LoRA
Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
This LoRA net is a tribute to one of my favourite artists.
For this you can use AnyLoRA (or any NAI based model).
around 0.9 weight for v1, while you should probably go over 1 for v2 (I like 1.25) . Lower weights give the coloration and pencil style, but not the distinctive shapes. Trigger is amano yoshitaka.
And it works with embeddings and other LoRA nets, so you can do the character you want in this style.
How to use LoRA's in auto1111:
Update webui (use
git pulllike here or redownload it)Copy the file to
stable-diffusion-webui/models/loraSelect your LoRA like in this video
Make sure to change the weight (by default it's
:1which is usually too high)
Mitwirkende
Modell-Details
Modelltyp
Basismodell
Modellversion
Modell-Hash
Trainierte Wörter
Ersteller
Diskussion
Bitte log in um einen Kommentar zu hinterlassen.









