Sign In

Genmoji - Flux

21

Updated: Jan 9, 2025

concept

Download

1 variant available

SafeTensor

18.39 MB

Verified:

Type
LoRA
Stats

146

21

69

Reviews
Published

Nov 22, 2024

Base Model

Flux.1 D

Training
Steps: 3,825
Epochs: 20
Usage Tips
Clip Skip: 1
Hash
AutoV2
3165A5A83D
default creator card background decoration
Likes - 12586

12.6K

Downloads - 166086

166.1K

Generations - 1054207

1.1M

Created on Civitai

The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.

IN NO EVENT SHALL BLACK FOREST LABS, INC. 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.

image (4).png

Genmoji LoRA is inspired by the new Genmoji feature in iOS 18.2, which uses AI to create personalized emojis based on text prompts. Similar to the functionality in iOS, this model enables the generation of unique and creative emoji-like visuals. Whether it’s a breakdancing astronaut or a dog playing the bagpipes, Genmoji LoRA helps you craft expressive and tailored emojis that elevate your communication and make your messages more dynamic.

Base Model:
Flux

Recommended Settings:

  • CFG: 2.0 - 3.5

  • Steps: 20 - 40

  • Strength: 0.5 - 1.0 (recommended: 0.5 if text-based output encounters issues)

Additional Information:

  • For text-heavy prompts or intricate emoji designs, a lower strength setting (around 0.5) is suggested for optimal results.

  • The model was trained on a dataset of 765 emojis, offering a vast range of creative possibilities for generating custom, emoji-style art.

  • Use Case Example: Personally, I’ve imported the generated images as stickers into Android messaging apps, where they work seamlessly and add a fun, personalized touch to conversations.

Note:
All sample images were created using a CFG value of 3.5 and step counts between 20 and 40. Fine-tuning parameters as needed will help achieve the best outcomes for your specific use case.