modèles/Toh-Yasu - Painting

Toh-Yasu - Painting

10/27/2025

5:51:24 PM

Mots-clés et tags associés

adel_ai,concept artist,emotional depth,flux.1 d,flux1.d model,graphical design,japanese illustrator,lora,painting,portrait illustration,style,toh-yasu,toyasu style

A painting of a dark-skinned man wearing a black fedora, white shirt with red suspenders, and a blue striped tie, standing in front of an abstract urban cityscape.

Realistic painting of a resting cougar with closed eyes on a ledge, illuminated by soft warm light in ToYasu style with detailed fur and muted earthy background.

A realistic painting of two fried eggs in a rustic metal frying pan with a spoon resting on the side, featuring textured warm green, orange, and brown background.

Paramètres recommandés

samplers

dpmpp_2m_sgm_uniform

steps

resolution

808x1298, 939x1117, 866x1210, 912x1150, 816x1285, 896x1152, 830x1264, 916x1145, 905x1159, 835x1256

vae

ae.sft

other models

Kreamania I.safetensors (87eec16010)

Conseils

The length of the prompt influences the expression of the model; the shorter the prompt, the more the model expresses itself.

Points forts de la version

Model trained on 185 images dataset.

Recommended resources : Fluxmania

Recommended inference : dpmpp_2m or heunpp2 / sgm_uniform / 20 steps / guidance : 3.5
Weighting : around 1.0

Sponsors du créateur

Showcase images were created with ComfyUI and are in PNG, include metadata & workflow. All licensing conditions for the Flux Dev model apply. You can find the details here.

Toh-Yasu (藤保 Toh-Yasu) is a Japanese illustrator and concept artist based in Fukuda, Japan.
Specializing in graphic design, illustration and compositional painting, he creates work spanning game logos, website art, splash illustrations, and promotional materials.
Toh-Yasu’s portraits, especially his pencil work, are noted for their emotional depth and delicate detail — subtle expressions, nuance, and atmosphere play a central role in his pieces.

NOTE : The length of the prompt influences the expression of the model, the shorter the prompt, the more the model expresses itself.

Showcase images were created with ComfyUI and are in PNG, include metadata & workflow. All licensing conditions for the Flux Dev model apply. You can find the details here.

IMPORTANT NOTE: This model is a tribute to the artist and not an attempt to copy or reproduce his works. Flux1.D is unable to reproduce a graphic universe on which it was trained, the goal is solely to expand Flux's pictorial capabilities.

VERY IMPORTANT NOTE : Do not like my models, do not give me buzz, do not follow me, otherwise you will be reported to Civitai for attempted corruption