<h1 id="artist-collection-study-b6lvgtuo6">Artist Collection - Study</h1>Collection of 25 curated and manually rated artist datasets:<pre><code>ajimita
ame929
ashima \(roro046\)
ask \(askzy\)
dino \(dinoartforame\)
diyokama
dsmile
fuzichoco
kinta \(distortion\)
konya karasue
lack
lam
lifeline \(a384079959\)
mika pikazo
miv4t
mizumi zumi
nid417
quasarcake
ruoganzhao
say hana
timbougami
tokkyu
wanke
xixun
yoneyama mai
z3zz4</code></pre>These artists tags are already trained in Illustrious/noobai, (see <a target="_blank" rel="ugc" href="https://civarchive.com/posts/10535627">x/y/z plot references</a>) this is an attempt to further train on specifc works to appreciate and study their styles.Recommended prompt structure:Positive prompt:<pre><code>by {artist},
{{tags}}
masterpiece, best quality, very awa, absurdres</code></pre>Negative prompt:<pre><code>(worst quality, low quality:1.1), bad anatomy, bad hands, watermark, ugly, distorted, signature</code></pre>I trained the artists datasets together to experiment with artist tag combinations and prompting techniques like <a target="_blank" rel="ugc" href="https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#alternating-words">alternating words </a>for swapping on each step:<pre><code>by [say hana|wanke|diyokama|yoneyama mai]</code></pre>

Artist Collection - Study

Trained on <a target="_blank" rel="ugc" href="https://civitai.com/models/833294?modelVersionId=1116447">NoobAI-XL (NAI-XL) Epsilon-pred 1.1-Version</a>

noobai_epred_11_artists_v11.safetensors

v1.1 [noobai-e-pred-1.1]

Artist Collection - StudyCollection of 25 curated and manually rated artist datasets:ajimita ame929 ashima \(roro046\) ask \(askzy\) dino \(dinoartforame\) diyokama dsmile fuzichoco kinta \(distortion\) konya karasue lack lam lifeline \(a384079959\) mika pikazo miv4t mizumi zumi nid417 quasarcake ruoganzhao say hana timbougami tokkyu wanke xixun yoneyama mai z3zz4These artists tags are already trained in Illustrious/noobai, (see <a target="_blank" rel="ugc" href="https://civitai.com/posts/10535627">x/y/z plot references</a>) this is an attempt to further train on specifc works to appreciate and study their styles.Recommended prompt structure:Positive prompt:by {artist}, {{tags}} masterpiece, best quality, very awa, absurdresNegative prompt:(worst quality, low quality:1.1), bad anatomy, bad hands, watermark, ugly, distorted, signatureI trained the artists datasets together to experiment with artist tag combinations and prompting techniques like <a target="_blank" rel="ugc" href="https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#alternating-words">alternating words </a>for swapping on each step:by [say hana|wanke|diyokama|yoneyama mai]

noob-epred-1.1

<h1 id="artist-collection-study-b6lvgtuo6">Artist Collection - Study</h1>Collection of 25 curated and manually rated artist datasets:<pre><code>ajimita
ame929
ashima \(roro046\)
ask \(askzy\)
dino \(dinoartforame\)
diyokama
dsmile
fuzichoco
kinta \(distortion\)
konya karasue
lack
lam
lifeline \(a384079959\)
mika pikazo
miv4t
mizumi zumi
nid417
quasarcake
ruoganzhao
say hana
timbougami
tokkyu
wanke
xixun
yoneyama mai
z3zz4</code></pre>These artists tags are already trained in Illustrious/noobai, (see <a target="_blank" rel="ugc" href="https://civitai.com/posts/10535627">x/y/z plot references</a>) this is an attempt to further train on specifc works to appreciate and study their styles.Recommended prompt structure:Positive prompt:<pre><code>by {artist},
{{tags}}
masterpiece, best quality, very awa, absurdres</code></pre>Negative prompt:<pre><code>(worst quality, low quality:1.1), bad anatomy, bad hands, watermark, ugly, distorted, signature</code></pre>I trained the artists datasets together to experiment with artist tag combinations and prompting techniques like <a target="_blank" rel="ugc" href="https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#alternating-words">alternating words </a>for swapping on each step:<pre><code>by [say hana|wanke|diyokama|yoneyama mai]</code></pre>

Files with SHA256: b095cafc81e34ef87e47997186d1cd190bb71db5ea5c143bd40ab19e4b8f12e5