Sign In

Backlit Silhouette [Klein 9B]

0

Updated: Jul 8, 2026

concept

Download

1 variant available

bf16 SafeTensor

KleinBase9B_BacklitSilhouette_V1.0.safetensors

BF16, good balance • 79.03 MB

Verified:

Type
LoRA
Stats

147

0

Reviews
Published

Jun 27, 2026

Base Model

Flux.2 Klein 9B-base

Training
Steps: 1,500
Usage Tips
Strength: 1
Hash
AutoV2
426459C22D
Trigger Words
<color> backlit silhouette
default creator card background decoration
Uploads - 106

106

Followers - 349

349

Downloads - 45261

45.3K

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.

ComfyUI_lora_00001_.png

This model allows you to create a dramatic effect where the characters are backlit by a light of the chosen color. The base model has some functionality to do this, however I've found that it tends towards completely removing or obscuring the background in favor of solid light and it can also struggle with creating a natural diffused light on the edges of the subject.

If the character is wearing bulky clothing (like armor), it will try to change them into simple attire that is generally more form-fitting to allow the character outline to be seen, and if they are wearing hanging or loose-fitting clothing, it will also opt for the clothing to be slightly translucent in order to have some light to flow through in order to allow the character outline to actually be seen.

The general trigger for the effect is:

<color> backlit silhouette

You can suppress or guide the outfit change as desired with the following phrase:

preserve the person's outfit

California AB 2013 Training Data Disclosure

  • This LoRA was fine-tuned using visual data consisting of image pairs. The training data may include copyrighted material owned by third parties. No training data was licensed or purchased. This LoRA is provided for non-commercial use only under the terms of its distribution.

  • The dataset consists of about 250 images in total, which are a mix of synthetic data and frames from videos that were posted to publicly available locations online. This is the total used for training after low quality sets were culled. Dataset was collected/created in 2026.

  • Data was processed through standard resizing, cropping, normalization, and labeling steps. Synthetic images were included as part of the training dataset.

  • This model is intended for non-commercial, experimental, and educational use. Generated outputs may reflect copyrighted visual styles or themes associated with the underlying training data. Users are responsible for ensuring compliance with applicable copyright law, other intellectual property laws, and all other applicable laws.