[SD 1.5][Checkpoint]ColorfulCocktail V1.0
<p>By downloading, you agree to the<a target="_blank" rel="ugc" href="https://huggingface.co/spaces/CompVis/stable-diffusion-license"> <u>CreativeML Open RAIL-M</u></a></p><p>This is an all-around model for anime to semi-realistic.</p><p>Pros:</p><ul><li><p>Great results with few words</p></li><li><p>Multiple subjects</p></li><li><p>Intense bright colors</p></li><li><p>Favors symmetry</p></li><li><p>Can use Danbooru tags, long sentences, or both</p></li><li><p>Works well with embeddings and hypernetworks</p></li></ul><p>Cons:</p><ul><li><p>No photorealism</p></li><li><p>Poses can be tricky to summon correctly</p></li><li><p>Long heavily emphasized prompts are penalized</p></li><li><p>Sexual acts almost always lead to a Cronenberg fever dream</p></li></ul><p>Tips:</p><ul><li><p>To get intense colors, use (monochrome) in the negativ with psychedelic in the positiv</p></li><li><p>Highly recommending playing around with clip skip<br /></p></li></ul><p>VAE used : AnythingV3<br /></p><p>By downloading, you agree to any licenses listed below.</p><p>Models used:</p><ul><li><p>Anything-v3.0</p></li><li><p>EimisAnimeDiffusion_1.0v</p></li><li><p>ACertainModel</p></li><li><p>F222_v1</p></li><li><p>Dreamlike-diffusion-1.0 (<a target="_blank" rel="ugc" href="https://civitai.com/models/1274/dreamlike-diffusion-10"><u>license</u></a>)</p></li></ul>
页:
[1]