|
|
--- |
|
|
tags: |
|
|
- text-to-image |
|
|
- lora |
|
|
- diffusers |
|
|
- template:diffusion-lora |
|
|
widget: |
|
|
- text: >- |
|
|
rule of third, concept art, dutch angle action pose (wabi-sabi clockwork |
|
|
cyborg:0.9) (android robot face::2.2),white ceramic material,many mechanical |
|
|
details,seams, scuffing, (camera lenses instead of pupils:1.5) (traditional |
|
|
intricate japan clothes:1.5) (style by Yuri Shwedoff),shallow depth of |
|
|
field, vignette, (Fujicolor Superia X-TRA 400) style by Nirav Patel, inside |
|
|
a fractal shaped Artemis Station spaceport megastructure, perfect focus, |
|
|
depth of field the view from afar, window view. vast scifi cyberpunk |
|
|
landscape, internal gears, inside, cogs and wheels, |
|
|
<lora:mechanica_v42_rank32_bf16-step00456:1>, clckwrk |
|
|
parameters: |
|
|
negative_prompt: 'Guidance: 1 Steps: 20 Seed: 2703591443' |
|
|
output: |
|
|
url: images/00084-2703591443.jpeg |
|
|
- text: >- |
|
|
A nude female warrior stands poised with a katana, exuding confidence and |
|
|
strength. She is a mechanical clockwork girl moved by tiny gears inside her |
|
|
arms and legs, cogs and wheels, clockwork gears seen through her transparent |
|
|
skin in her chest. Intricate details, moving parts, swinging swords, |
|
|
completely naked, <lora:mechanica_v42_rank32_bf16-step00456:1>, clckwrk |
|
|
parameters: |
|
|
negative_prompt: 'Guidance: 1 Steps: 20 Seed: 4132606917' |
|
|
output: |
|
|
url: images/00117-4132606917.jpeg |
|
|
- text: "clckwrk, A clockwork medieval knight in full armor, featuring a blend of polished brass and steel plates. Gears and cogs are visible in the joints and along the chest plate, with a mechanical visor that opens to reveal glowing eyes. The knight holds a sword with a gear-driven hilt, and his shield is adorned with clockwork emblems. The background is a foggy battlefield, enhancing the knightâ\x80\x99s metallic details., <lora:mechanica_v42_rank32_bf16-step00456:1>" |
|
|
parameters: |
|
|
negative_prompt: 'Guidance: 1 Steps: 20 Seed: 4117752936' |
|
|
output: |
|
|
url: images/00101-4117752936.jpeg |
|
|
base_model: black-forest-labs/FLUX.1-dev |
|
|
instance_prompt: clckwrk |
|
|
license: unknown |
|
|
--- |
|
|
# Mechanica: Clockwork Concept |
|
|
|
|
|
<Gallery /> |
|
|
|
|
|
## Model description |
|
|
|
|
|
FROM https://civitai.com/models/912513/mechanica-clockwork-concept |
|
|
|
|
|
Trigger clckwrk |
|
|
Strength 1 |
|
|
|
|
|
The Art of Clockwork Creation |
|
|
Enter a world of intricate clockwork art and mechanical creatures with Mechanica, a LoRA designed to transform your subjects into creations of gears, cogs, and metallic beauty. Inspired by a mix of steampunk, clockwork sculptures, and mechanized industrial fantasy, Mechanica reimagines animals, people, and objects as finely crafted clockwork automata. It'll create anything from vigilant clockwork animals with jeweled eyes to mechanical armor-adorned warriors. |
|
|
|
|
|
Flux thinks anything clockwork just needs to look steampunk, but this LoRA will add gears, cogs, and wheels that are needed to really make it into a clockwork automaton. It also makes cool mechanical machines and fine clockwork parts for actual clocks. |
|
|
|
|
|
Usage |
|
|
To use the most recent version of the LoRA, use the following settings: |
|
|
|
|
|
Trigger word: clckwrk |
|
|
|
|
|
Other tokens that work well: describing subjects as "clockwork" or "mechanical" help things go in the right direction. In addition, explain how you want the "gears" "cogs" and "wheels" to look. |
|
|
|
|
|
Lora Strength: A strength between 0.8 and 1.2 is recommended for Flux prompts written in natural language, but pull back to 0.6 to 1.0 for Danbooru tag Flux prompts that usually name more anime-style images. |
|
|
|
|
|
For differences in previous versions, see the version notes below. |
|
|
|
|
|
Version Notes |
|
|
So, starting with v4.2 may seem odd, but this concept was surprisingly difficult to train. |
|
|
|
|
|
Version 4.2 |
|
|
After trying out many variations, I discovered that the concept trained better with just four images over the 20 or so I had tried to use in v1 and v2 (failed versions). Training this LoRA at 512 resolution worked better than 1024, with a batch size of 4 working better than 1. Captioning was also tricky, so I had to describe things as if they were not clockwork to get the training to stick. It mainly will work for animals and some people, but I've managed to get some excellent clockwork items as well. |
|
|
|
|
|
|
|
|
## Trigger words |
|
|
|
|
|
You should use `clckwrk` to trigger the image generation. |
|
|
|
|
|
|
|
|
## Download model |
|
|
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
|
|
[Download](/Jonjew/MechanicaClockwork/tree/main) them in the Files & versions tab. |
|
|
|