ghost
Sign In

3D Cartoon Vision FLUX

65
619
432
31
Verified:
SafeTensor
Type
LoRA
Stats
619
432
Reviews
Published
Aug 19, 2024
Base Model
Flux.1 D
Training
Steps: 15,000
Usage Tips
Strength: 0.8
Hash
AutoV2
E4A2D4B7E4
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.

3D Cartoon Vision FLUX

It’s my first 3D cartoon model based on FLUX, and it includes NSFW support, which has produced pretty good results in testing.

  • Trigger Word: Not necessary, but if you prefer to use one, try "3D cartoon."

  • NSFW Support: Yes . Up 😛 down 🤮

Note: This LoRA training is ongoing. Once it’s complete, I will start merging it with a checkpoint soon.

Training Configuration:

  • GPU: A6000

  • Dataset Size: 1200 images

  • Captioning Tool: WD14

  • Batch Size: 1

  • Optimizer: AdamW

  • Learning Rate: 1e-04

  • Total training steps: 15k

  • Training Duration: 14h+

Please note that all my FLUX LoRA models are still experimental, so you might encounter some issues. If you do, please let me know in the comments section. Your feedback is valuable for future improvements!

Recommended Parameter :

  • LoRA Weight : 0.5➡1

  • Sampler : euler

  • Steps : 20

  • CFG : 1

Join my community, Share your feedback, learn, and have fun with us! 😊

Discord➡️https://discord.gg/QQKd7bu97P