fantasy-wizard-witches

Fantasy Wizard & Witches

<Gallery />

Model description

<h1 id="fantasy-wizard-and-witches-bql1k9cy0">Fantasy Wizard &amp; Witches</h1><h3 id="hello-friends!-onf6757w7"><strong><span style="color:rgb(64, 192, 87)">Hello friends!</span></strong></h3><h3 id="flux-version-2-is-now-out-with-more-magical-images!!-7grim8gyp"><strong><span style="color:rgb(64, 192, 87)">Flux version 2 is now out with more magical images!!</span></strong></h3>><h3 id="things-to-know:-ozdqtr49d">Things To know:</h3><ul><li><p><span style="color:rgb(18, 184, 134)">You should use the trigger word</span> <strong><em><span style="color:rgb(64, 192, 87)">HKMagic</span></em></strong></p></li><li><p><strong><span style="color:rgb(21, 170, 191)">This LoRA works very well in adding details to images!</span></strong></p></li><li><p><strong><span style="color:rgb(253, 126, 20)">Most of the images in dataset has a book in one hand so try to prompt spellbook in one hand.</span></strong></p></li></ul><p></p><h3 id="xl-usage-tips-:-8sy8cxeer">XL Usage Tips :</h3><ul><li><p><span style="color:rgb(193, 194, 197)">The LoRA weight I have been using is 0.85, but feel free to try and experiment!</span></p></li><li><p><span style="color:rgb(193, 194, 197)">I have used ComfyUI when generated pictures and the settings im using are:</span><br /><span style="color:rgb(193, 194, 197)">Sampler: </span><strong><span style="color:rgb(193, 194, 197)">dpmpp_3m_sde</span></strong><br /><span style="color:rgb(193, 194, 197)">Scheduler: </span><strong><span style="color:rgb(193, 194, 197)">Karras</span></strong><br /><span style="color:rgb(193, 194, 197)">Steps: </span><strong><span style="color:rgb(193, 194, 197)">40</span></strong><br /><span style="color:rgb(193, 194, 197)">cfg: </span><strong><span style="color:rgb(193, 194, 197)">3.6</span></strong></p></li><li><p><span style="color:rgb(130, 201, 30)">Example prompts used:</span></p><p>"A beautiful fairy with glowing wings reads an ancient book of magic and spells. She has detailed facial features and there is a glowing green light in the background with cinematic lighting, fairycore, hkmagic"</p></li><li><p>First image is with my LoRA and second is without my LoRA, same prompt and model.<br /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c3a9ecd2-2de6-4f36-80d9-c56d644b890c/width=525/c3a9ecd2-2de6-4f36-80d9-c56d644b890c.jpeg" />Recomended vae that I use is the official <strong>sdxl_vae</strong></p></li></ul><h3 id="flux-usage-tips:-v3wq2eomc">Flux Usage Tips:</h3><ul><li><p><span style="color:rgb(193, 194, 197)">The LoRA weight I have been using is 0.85 - 1, but feel free to try and experiment!</span></p></li><li><p><span style="color:rgb(193, 194, 197)">Steps: </span><strong><span style="color:rgb(193, 194, 197)">40</span></strong><br /><span style="color:rgb(193, 194, 197)">cfg: </span><strong><span style="color:rgb(193, 194, 197)">3.6</span></strong></p></li><li><p><span style="color:rgb(130, 201, 30)">Example prompts used version 2:</span></p><p>"An evil necromancer witch casting colorful magic from her skeleton wand, purple black necrotic green, necrotic dark green armour made of bones and skulls, magical particles in the air, rusty skull armour, casting screaming tranparent skulls, face covered in glowing skull mask, hkmagic"</p></li><li><p>First image is with my LoRA and second is without my LoRA, same prompt and model.<br /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/7408c5de-8ee5-44ac-b70e-86d2917e45a6/width=525/7408c5de-8ee5-44ac-b70e-86d2917e45a6.jpeg" /></p></li></ul><h1 id="please-enjoy-and-share-your-amazing-work!-j8b1g4xh3"><span style="color:rgb(230, 73, 128)">Please enjoy and share your amazing work!</span></h1>

Trigger words

You should use hkmagic 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('Keltezaa/fantasy-wizard-witches', weight_name='FantasyWizardWitchesFluxV2-000001.safetensors')
image = pipeline('`hkmagic`').images[0]

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