Updated: Oct 25, 2024
styleVerified: 7 months ago
SafeTensor
Type | |
Stats | 321 84 443 |
Reviews | (50) |
Published | Oct 24, 2024 |
Base Model | |
Training | Steps: 688 Epochs: 10 |
Usage Tips | Clip Skip: 1 Strength: 1 |
Hash | AutoV2 D9CE99F95B |
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 revised DaVinci Ink Sketch Flux LoRa using the same training data as in my successful SDXL version. I made the training images with Dalle3. While the SDXL LoRa is awesome, the first flux attempt really didn't perform well. Happily I learned a bit about how to train flux, and this one seems a bit better. Try it out and let me know what you think!
In changing the training from tags to captions, I eliminated specific trigger words, however you can really bring out the style by adding stuff like:
Mechanical / Bio-mechanical
Robot
Parchment paper
Sepia
Annotations
Anatomical / Medical Study
Renaissance
Davinci
Pen and Ink sketch
Half mechanical, half human
Gears
Davinci's notebooks