This is a merge of a curated set of checkpoints to incorporate data that's been trained onto the Pony v6 checkpoint.The specific merge technique used aims to maintain as many strengths of each merged model while minimizing conflict and "drowning" from tension between them. This is a custom technique I have developed.<h2 id="prompt-apnv4x4wd">Prompt</h2>Pony prompt guidelines as per usual, for example:Positive:<pre><code>score_9, score_8_up, score_7_up,</code></pre>Negative:<pre><code>score_6, score_5, score_4, source_furry, source_cartoon</code></pre><h2 id="inference-ju62td2dq">Inference</h2>I recommend 20-30 steps, Euler A or DPM++ SDE Karras

populace

populace_v10.safetensors

v1.0

Positive:

score_9, score_8_up, score_7_up,
Negative:

score_6, score_5, score_4, source_furry, source_cartoon
Inference
I recommend 20-30 steps, Euler A or DPM++ SDE Karras

Files with SHA256: d53ff2f911037aa7fd5bdd195673b131e33585eac59597cbce8d772dce30141a