modelle/Toh-Yasu - Painting

Toh-Yasu - Painting

Adel_AI

10/27/2025

5:51:24 PM

| Discussion|

Empfohlene Parameter

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)

Tipps

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

Versions-Highlights

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

Ersteller-Sponsoren

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