SDXL_Niji_Seven - SDXL_Niji_v6
Parole Chiave e Tag Correlati
Prompt Consigliati
best quality
Prompt Negativi Consigliati
(worst quality, low quality, normal quality, bad quality, lowres:1.2), extra fingers, missing fingers, poorly rendered hands, mutation, mutated hands, deformed iris, deformed pupils, missing arms, missing hands, long neck, poorly drawn, poorly drawn eyes, watermark, poorly drawn hands, extra legs, poorly drawn iris, poorly drawn pupils, blurry, text, signature, web adress, bad iris, bad pupils, incoherence, inconsistency
Parametri Consigliati
samplers
steps
cfg
Suggerimenti
Don't hesitate to play with things like: realistic, hyper realistic, anime studio, digital artwork, illustration.
Clip skip -2 or -3 is recommended (-3 better overall).
A minimum of 26 steps is advised.
CFG scale between 3.5 and 6 is recommended.
Sampling method DPMPP_SDE Karras is best quality, Euler_Ancestral simple is second best, DPMPP_2M_SDE Karras or ddim simple are average quality.
Punti Salienti della Versione
A brand new dataset of more than 1200 images. A Keyword “NijiEX style”
Two Niji training merge to balance style and quality.
Sponsor del Creatore
All models are exclusive to Civitai ! Anyone who publishes my models without my consent will be reported!
All models are exclusive to Civitai ! Anyone who publishes my models without my consent will be reported!
Hi all!
SDXL_Niji_Seven is available!
I have incredible results with my LoRa model SDXL_Niji_V6_DLC_LoRa_ v2 at strength 0.5!
https://civitai.com/models/541460?modelVersionId=601994
I haven't tested v4 yet
What's new?
-This version is very different because it is based on NijiV6 To be more precise, around 1000 images from NijiV5 and 1600 from v6 (compared to a total of 1300 images in v6).
-I chose not to use the "expressive" style of NijiV5 this time. But maybe I will add it in a 7.5 version in the future.
-There is no longer a trigger word
-Version 6 is very different so I still recommend it.
Some tips for use:
-Don't hesitate to play with things like: realistic, hyper realistic, anime studio, digital artwork, illustration...
-Clip skip -2 or -3 is recommended (-3 better overall)
-A minimum of 26 steps
-cfg scale: between 3.5 and 6
-Sampling method: DPMPP_SDE Karras (recommended, best quality), Euler_Ancestral simple (2nd best), DPMPP_2M_SDE Karras or ddim simple (average quality for both).
Have fun ! 😊
Contributore
Dettagli del Modello
Tipo di modello
Modello base
Versione del modello
Hash del modello
Parole addestrate
Creatore
Discussione
Per favore log in per lasciare un commento.





