wizard-s-arcana-spectral-glow

Wizard's Arcana: Spectral Glow

<Gallery />

Model description

<p><strong><span style="color:rgb(253, 126, 20)">Wizard’s Arcana – Spectral Glow</span></strong><br />This LoRA brings an ethereal and gritty (fever-)dreamlike aesthetic, with lots of anomalies, distortions and lighting effects. </p><p>Trained on dataset full of light leaks, motion blur, inverted color, grain.</p><p>Prompt inspiration:<span style="color:rgb(193, 194, 197)"> </span><code>spectral glow</code><span style="color:rgb(193, 194, 197)">, </span><code>chromatic grain</code><span style="color:rgb(193, 194, 197)">, </span><code>motion blur</code><span style="color:rgb(193, 194, 197)">, </span><code>diffuse silhouette</code><span style="color:rgb(193, 194, 197)">, </span><code>light leak effect</code><span style="color:rgb(193, 194, 197)">, </span><code>prism effect</code><span style="color:rgb(193, 194, 197)">, </span><code>inverted negative film</code><span style="color:rgb(193, 194, 197)">, </span><code>ethereal</code><span style="color:rgb(193, 194, 197)">, </span><code>light background</code><span style="color:rgb(193, 194, 197)">, </span><code>dark background</code></p><p><strong>It is a fun model to experiment with. Try; </strong><br />• Prompts that describe mood and themes rather than subjects and action<br />• Add a couple of colors, and define the background as dark or light.<br />• Stream of conciousness-prompting – just put in word that sound good<br />• Using a higher guidance than normal<br />• Combining with other LoRAs<em>.</em></p><p><em>It will default to portraits, so keeping character descriptions to a minimum will bring out more effect.</em></p><p><em>Please share your creations in the gallery </em><strong>❤</strong></p>

Trigger words

You should use spectral glow, chromatic grain to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('WizWhite/wizard-s-arcana-spectral-glow', weight_name='Wiz-Arcana-Spectral_Glow.safetensors')
image = pipeline('spectral glow, chromatic grain, The Queen of Hearts from Alice in Wonderland').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers