Verified: 3 months ago
SafeTensor
Type | |
Stats | 34 0 |
Reviews | (2) |
Published | Feb 17, 2025 |
Base Model | |
Trigger Words | J0hnnyD |
Hash | AutoV2 DD33BCFF5D |
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.
This is my first attempt at a lora (at least one that turned out alright). I was testing a workflow to make headshots, and I wanted to create a lora using only a handful of images to see how it would come out.
This seems to work at a .8-1 strength and does decently well when doing a close-up image (like a headshot), for images with more going on, I'd recommend using a face detailer with this lora.
Every image has a grainy look to it, which I'm not sure why as my training images didn't have that look. But it makes the images look like they're from the 80s, so that can look cool.