Sign In

[MMH3] Wanted dead or alive

2

Updated: Sep 25, 2026

conceptwantedwild westposter

Loaded

Download

1 variant available

fp32 SafeTensor

MMH3-WantedPoster-V1.safetensors

Full precision, largest file • 24.09 MB

Verified:

Type
LoRA
Stats

163

2

54

Generation

Loaded

Reviews
Published

Sep 25, 2026

Base Model

MiniMax H3

Usage Tips
Strength: 1
Hash
AutoV2
77C4304C38
Trigger Words
A wanted dead or alive poster of a <type> named <name> with reward value of $<price>, on the end a <object> is throw at the poster
default creator card background decoration
Reactions - 171275

171.3K

Followers - 11694

11.7K

Downloads - 691704

691.7K

Halloween 2024 Contest Winner

Generation, training and LoRA distribution on Civitai are covered by Civitai’s own license agreement with MiniMax. If you download these weights and run them yourself, your use is instead governed by the MiniMax H3 Community License Agreement, whose grant excludes the European Union, the United Kingdom, the Republic of Korea and the United States of America.

MiniMax H3

Wanted Poster

Turn almost any subject into a dramatic old-western “WANTED DEAD OR ALIVE” poster.

Recommended strength: 1.0

I2V

Use a first frame containing the subject you want to transform, then use:

A wanted dead or alive poster of a <type> named <name> with reward value of $<price>, on the end a <object> is throw at the poster.

Example:

A wanted dead or alive poster of a mouse named DIRTY RAT with reward value of $80,086, on the end a knife is throw at the poster.

The first frame establishes the subject while the prompt controls the wanted-poster transformation.

T2V

Describe your scene and subject normally, then use the trigger phrase when you want the transformation:

A wanted dead or alive poster of a <type> named <name> with reward value of $<price>

The effect works with people, animals, plants, objects, vehicles, machines, tools, and other subjects.

Al my videos have WF embedded and can be used to teach you how to use it.

Strength 1.0 is recommended. Results may vary depending on the base model, prompt, first frame, and other LoRAs.