Keltezaa/flux-fantasy-knights-by-hailoknight

Flux Fantasy Knights - By HailoKnight

<Gallery />

(CivitAI)

Model description

<h1 id="flux-fantasy-knights-by-hailoknight-vf3tsqk2z">Flux Fantasy Knights - by HailoKnight</h1><h2 id="version-2-is-now-out-bit-a-big-new-dataset!!-5uh5rp8tr"><span style="color:rgb(64, 192, 87)">Version 2 is now out bit a big new dataset!!</span></h2><p></p><h3 id="things-to-know:-wosd6205b">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)">HKStyle</span> </em></strong><span style="color:rgb(18, 184, 134)">(For best results of course add some "holding sword", "Wearing armor" )</span></p></li><li><p>Works with swords and without.</p></li><li><p><strong><span style="color:rgb(253, 126, 20)">Dont want helmet? Add helmet to negative prompt or describe the hair!</span></strong></p></li></ul><p></p><h3 id="usage-tips-:-wu70a1ny5">Usage Tips :</h3><ul><li><p><span style="color:rgb(193, 194, 197)">The LoRA weight I have been using is 0.6-1, but feel free to try and experiment!</span></p></li><li><p><span style="color:rgb(193, 194, 197)">Check prompt examples on my uploaded images.</span></p></li><li><p><span style="color:rgb(193, 194, 197)">Cant provide more currently because I cant run it my self hehe.</span></p><p></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/bf1f717e-1f24-4d87-b703-e8d5c56e9bda/width=525/bf1f717e-1f24-4d87-b703-e8d5c56e9bda.jpeg" /></p></li></ul><h1 id="please-enjoy-and-share-your-amazing-work!-q6sjgc0bt"><span style="color:rgb(230, 73, 128)">Please enjoy and share your amazing work!</span></h1>

Trigger words

You should use hkstyle 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/flux-fantasy-knights-by-hailoknight', weight_name='FluxFantasyKnightV2Test.safetensors')
image = pipeline('a cinematic shot of a mechanical robotic knight, glowing blue core, holding a giant blue glowing plasma sword by the handle, mecha wings on helmet, futuristic background, HKStyle, mythp0rt  ').images[0]

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