Sign In

Caught_by_light

23
162
84
10
Verified:
SafeTensor
Type
LoRA
Stats
162
84
253
Reviews
Published
Jan 17, 2025
Base Model
Flux.1 D
Training
Steps: 270
Epochs: 5
Usage Tips
Clip Skip: 1
Strength: 1
Trigger Words
Caught_by_light
in the darkness
Training Images
Download
Hash
AutoV2
D60FF2AB1F
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.

Caught_by_light creates dramatic images of scenes with light from above or behind. Characters or items that are the focus of the lora may be cast in shadow and seen only in silhouette while a light shines over their shoulder; they may be surrounded by crepuscular rays from above, as a divine being or alien visitor reaches out to them; a ray of sunshine through a blind could highlight a sleeping form.

It works best with prompts in the form of "Caught_by_light your character or object in the darkness".
Leaving off "in the darkness" will still get crepuscular rays or backlighting, but they'll be less of a feature as the generated image will be brighter overall.
Long prompts should come after both, to avoid the effect getting lost.

A strength of 1 is usually sufficient; 1.5 works as well. 2 can work, but will sometimes throw up some degraded graphical effects.