Sign In
homemodelsimagesvideos3D Modelshubsarticlescomicscruciblesupdatesshop

USDOT Hazard Placards

47

Updated: Jun 18, 2026

conceptusdotindustrialsignwarninghazard

Not loaded

Download

1 variant available

SafeTensor

87.61 MB

Verified:

Type
LoRA
Stats

141

47

55

Generation

Not loaded

Reviews

(29)

Published

Jun 18, 2026

Base Model

Anima

Training
Steps: 1,700
Epochs: 10
Hash
AutoV2
B434BD9F0F
Trigger Words
USDOT_Placard, diamond shaped, orange sign, black linework only, no background, text-free image, (silhouette:1.25), simple image of a side view of a ...
USDOT_Placard, hazard, warning, sign, diamond shaped, white sign, red sign, simple image of a flame in black, duocolor, bicolor, white on top half, red on bottom half, white on top half and red on bottom half, text that reads "SPONTANEOUSLY COMBUSTIBLE" in the center, hazard class "4", no background,
USDOT_Placard, hazard, warning, sign, diamond shaped, white sign, white trim, white placard with white trim, simple line drawing of a skull and crossbones, text that reads "POISON", hazard class "6", no background,
default creator card background decoration
Reactions - 15942

15.9K

Likes - 4217

4.2K

Downloads - 32504

32.5K

ODOR Badge

License:

Anima

The Anima Model is licensed by CircleStone Labs LLC. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

Built on NVIDIA Cosmos

1.png

Anima

Specialized to make highly industrial looking diamond shaped signs. Try some experiments as this LoRA is a lil' tricky to use. Some cherry picking may be needed.

The data was fairly hard to track down for this one. So some upscaled low res images made it into the dataset. I foolishly upscaled at nearest, which usually is fine - but in this case it can kind of make some generations look blocky and low resolution. Add low resolution and use quality tags to avoid this. In the future with another version - I won't make that same mistake.

Best at 1:1 square ratios

Trained at 768x768

Weights are good in a high range 0.5 - 1.0+