Today’s issue

• AIによる画像作成はかわいい女の子の例はたくさんある
• 風景画像の例が少ない
• 風景画像を描きたい

Today’s Solution

• 風景画像に強いモデルを指定してStable Diffusionを立ち上げる。

方法

以下をモデルの部分に指定してStable Diffusionを立ち上げる

Photography And Landscapes
!wget https://civitai.com/api/download/models/9077 -O /content/stable-diffusion-webui/models/Stable-diffusion/photographyandlandscapes_.safetensors
!wget https://huggingface.co/WarriorMama777/OrangeMixs/resolve/main/VAEs/orangemix.vae.pt -O /content/stable-diffusion-webui/models/Stable-diffusion/orangemix.vae.pt

立ち上げ方その他Stable Diffusionの基本的な操作方法については以前の記事を参照。

私が試したプロンプトは以下

Prompt

Norwegian Wood, Haruki Murakami, Listen to the Wind Sing, landscape photography. vivid colors, ambient lighting, excellent composition, dynamic dramatic cinematic lighting, aesthetic, very inspirational,  Wood, Haruki Murakami, Listen to the Wind Sing, landscape photography. with kitsune mask and a dragon made of wood. intricate, elegant, highly detailed, digital painting, artstation, concept art, sharp focus, illustration, by justin gerard and artgerm, 8 k

Negative prompt:

erotic, nsfw, glasses. bad anatomy, bad hands, text, missing fingers, extra digit, fewer digits, signature, watermark, username, blurry, artist name, abstract, picasso, amputee, deformed, blurry, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands, extra leg, bar censoring, blurry face, out of frame, border

Seed:

2608711493

その他

Size: 768x512, Seed:2608711493, Steps: 20, Sampler: Euler a, CFG scale: 10