Sign In

Flux1[dev]-AsianLoRA

269
3.6k
513
89
Updated: Oct 2, 2024
style
Verified:
SafeTensor
Type
LoRA
Stats
2,594
340
Reviews
Published
Aug 9, 2024
Base Model
Flux.1 D
Training
Steps: 2,500
Epochs: 1
Usage Tips
Strength: 0.6
Trigger Words
a young woman
Hash
AutoV2
3C31291CF5
Witch's Brew Badge
fok3827's Avatar
fok3827
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.

What's different about version 2.0?

After over a month of more than 10 attempts, I finally chose to train with DoRA, aiming to minimize its impact on limb positioning while handling larger datasets. Just when my patience was about to run out, I was pleasantly surprised by the results.
I welcome everyone to test it out and share their feedback. I also apologize for not being able to keep up with your comments during this time.

==============================

This LoRA (Low-Rank Adaptation) is experimental, aimed at exploring the feasibility of training LoRA with Flux.

The LoRA can make the default female appearance in Flux lean more towards an Asian look. However, it has not undergone any facial beautification or "internet celebrity face" training.

Usage:

It is recommended to use weights between 0.4 and 0.65. The latest version of ComfyUI now supports loading Flux LoRA.

Regarding Training:

The training was done using the SimpleTuner script with 2,900 images, taking approximately 20 hours.

Disadvantages/Issues:

There might be slight impacts on the limbs, with a minor decline in the overall performance of the model. More training or other methods may be needed.

It is challenging to fit, and the images may easily collapse during learning.

Testing:

The following are images generated by ComfyUI Flux1.dev-fp8, 25 steps, with prompts and seeds shown on the images: