Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
dreamlookai_stable-diffusion-v1-5_lora_step_1500_db_f6bf2132_ckp_98a875d8.safetensors
36 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<tinker-toy>
About This Model
STABLE DIFFUSION 1.5 · LoRAs
Created by
3VOLUTION
on Civitai
Lora created by Pirate Diffusion community member EVO. Per his civitai entry: I remember FONDLY the days of my childhood where everything was fresh, the world was yet to be discovered, and something as simple as 'Tinker Toys' were able to entertain me for hours on end. This is when I thought how cool would it be to explore Tinker Toys in a completely new age with endless possibilities. This LORA, in its initial phase, may not produce a perfect replica of this childhood classic but it sure is fun to work with. This LORA is fresh off the press and I am still trying to figure out all that it can do. I will try to post more images as I obtain them. Enjoy 👽 If this LORA were a steak it might be medium rare to medium. Meaning, might need to pump up the weight a bit but most models so far seem to tolerate the extra spice.
Creator notes
I remember FONDLY the days of my childhood where everything was fresh, the world was yet to be discovered, and something as simple as 'Tinker Toys' were able to entertain me for hours on end. This is when I thought how cool would it be to explore Tinker Toys in a completely new age with endless possibilities. This LORA, in its initial phase, may not produce a perfect replica of this childhood classic but it sure is fun to work with. This LORA is fresh off the press and I am still trying to figure out all that it can do. I will try to post more images as I obtain them. Enjoy 👽 If this LORA were a steak it might be medium rare to medium. Meaning, might need to pump up the weight a bit but most models so far seem to tolerate the extra spice. Edit2: This LORA seems pretty flexible. Placing earlier in prompt seems to emphasize the elements better. Try adding phrases like 'toy', 'playful', 'toys', even try with and with out the key word 'tinker toys' for more emphasis. IT also seems to be decent at realistic photo styles and can add interesting color schemes to photos/images.
Trigger words
tinker toys
518 downloads · 55 likes on Civitai
SHA256
A9111D1A05F1C8EEE8CF39D84501294147AEA1866D4E39BCB3F5D0E4AEBEE492
ModelTrends.ai Model ID
#6289
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Size
640x640
Prompt
Will add soon
Settings
Sampler
DPM++ 2M Karras
Steps
25
Guidance
7.5
Seed
278668
Size
640x960
Prompt
real, raw, toy commercial still <tinker-toy> epic castle, ultra detailed, fun, colorful
Negative prompt
sketch, worst quality, low quality
Settings
Sampler
DPM++ 2M Karras
Steps
30
Guidance
7
Seed
625472472
Size
512x768
Clip skip
9
Weight used
0.65
Prompt
An astonishing award winning photograph, sexy blue skin brunette mad-scientist in her retro-futuristic laboratory examining freakish, grotesque clones with bloated twisted contorted bodies laying in a bath of white liquid in jars, pulp-sf, weird future fashion, grainy film, 1970s Brazilian space-age Tropicalia retrofuturism, in the style of Pipilotti Rist
Negative prompt
low quality, watermark, low quality, illustration,children, bathtub
Settings
Sampler
DPM++ 2M Karras
Steps
50
Guidance
8
Seed
579582
Size
640x960
Prompt
<tinker-toy:1.0> real, raw, toy commercial still, epic statue, ultra detailed, fun, colorful
Negative prompt
sketch, worst quality, low quality
Settings
Sampler
DPM++ 2M
Steps
25
Guidance
8
Seed
830232
Size
1152x768
Prompt
<tinker-toy:1.5> , real, hdr, (toy commercial still), (Miami Beach, outdoor weight lifting area), (toy exercise equipment:1.5), epic human toy hybrid, 8k, hdr, dslr, ultra detailed, fun, colorful <dreamshaper7>
Negative prompt
2d, illustration, 3d, (worst quality:2), (low quality:2), (normal quality:2), ((monochrome)), ((grayscale)), bad anatomy, wrong anatomy, (cropped), extra eyebrow, collapsed eye shadow, (bad hands), poorly drawn, unnatural, long neck, poorly drawn eyes, error, (bad photo)
Settings
Sampler
DPM++ 2M Karras
Guidance
7
Seed
394562
Size
640x640
Prompt
<tinker-toy> helicopter <edge>
Settings
Sampler
DPM++ 2M Karras
Steps
50
Guidance
9
Seed
558718
Size
960x640
Prompt
raw photo of <tinker-toy:1.2>, yacht, expensive, playskool tinkers, retro, hdr, best quality <realvis30>
Negative prompt
(sketch, painting, worst quality, low quality, uninteresting, bad photo, cropped, deformed)
Settings
Sampler
DPM++ 2M Karras
Steps
50
Guidance
11
Seed
558717
Size
960x640
Prompt
raw photo of <tinker-toy:1.2>, yacht, expensive, playskool tinkers, retro, hdr, best quality <realvis30>
Negative prompt
(sketch, painting, worst quality, low quality, uninteresting, bad photo, cropped, deformed)
AI Models for Image, Video & Text Generation
tinker toy is a LoRA for the Stable Diffusion 1.5 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion 1.5 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models