wizard-s-scrap-yard-supermarionation-puppets

Wizard's Scrap Yard: Supermarionation Puppets

<Gallery />

(CivitAI)

Model description

<p><strong><span style="color:#fd7e14">Welcome to the Wizard's Scrap Yard</span></strong><br />Browse around and see if you find something you like. Mostly puppets here atm <br /></p><p>T H U N D E R B I R D S : <u><br /></u>A classic British puppet sci-fi TV-show from the 60s, which was the inspiration of Team America: World Police. The puppets were created by Sylvia Anderson who co-created the show with her husband Gerry Anderson.</p><p><span style="color:rgb(193, 194, 197)">Trigger: </span><code>Thunderbirds Puppet</code><span style="color:rgb(193, 194, 197)"> or simply </span><code>puppet</code></p><p>--</p><p>S K R O T N I S S E : <u><br /></u>Swedish puppet-animated series The Tale of Skrotnisse and His Friends (1985), a <br />LoRA that produces characters with exaggerated facial features.</p><p><span style="color:rgb(193, 194, 197)">Trigger: </span><code>puppet,</code><span style="color:rgb(193, 194, 197)"> can help.</span></p><p><span style="color:rgb(193, 194, 197)">LoRA strength between 0.7-1.2 </span><br /><a target="_blank" rel="ugc" href="http://Flux1.Dev"><span style="color:rgb(193, 194, 197)">Flux1.Dev</span></a><span style="color:rgb(193, 194, 197)"> Base seems to produce best output for me</span></p><p>Trained on screengrabs from tv-show based on the books by Jan Lööf. A show that has traumatized an entire generation of Swedes with its puppets' uncanny appearance.</p><p>• <span style="color:rgb(193, 194, 197)">45 low quality screengrabs trained at 512px res</span><br />• Minimal captions; <code>puppet, charactername</code><span style="color:rgb(193, 194, 197)"> </span><br />• <span style="color:rgb(193, 194, 197)">minSNRgamma: 2 and </span><span style="color:oklab(0.899401 -0.00192499 -0.00481987)">unetLR: 0.00035</span><br />• Final epoch was at only 675 steps</p><p></p><hr /><p></p><p>Sample of the original shows:</p><div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/1ESV9uw_Fkk" start="0"></iframe></div><p></p><p></p><div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/wLiH4xrCITI" start="0"></iframe></div><p><br /><strong><span style="color:rgb(193, 194, 197)">AI_Noire</span></strong><span style="color:rgb(193, 194, 197)"> created this amazing looking SDXL LoRA on the same concept. </span><br /><span style="color:rgb(193, 194, 197)"> </span><a target="_blank" rel="ugc" href="https://civitai.com/models/625708/skrotnisse-swedish-puppet-show-from-1985-sdxl-v1">https://civitai.com/models/625708/skrotnisse-swedish-puppet-show-from-1985-sdxl-v1</a><br />and </p>

Trigger words

You should use Thunderbirds Puppet, Puppet 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-scrap-yard-supermarionation-puppets', weight_name='Wiz-Thunderbird_Puppets.safetensors')
image = pipeline('tivoli fortune-telling machine, the automaton machine has a thunderbird puppet wizard whitebeard mannequin inside, neon light sign text reads "Wizard Speaks" and below "Make A Wish: 25 buzz"
').images[0]

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