Download
1 variant available
1,0840 1 2 3 4 5 6 7 8 9,0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
6340 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
3.4K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
(108)
Aug 20, 2024
Flux.1 D
Flux was able to get the concepts and style from the training data better in 5k steps than SDXL/Pony for 10k.
You can safely use Strength 2 and still get a decent results.
For recommended usage on Quantized version check this really simple ComfyUI Workflow:
https://civitai.com/models/658639/super-simple-gguf-quantized-flux-lora-workflow
All the images from the Showcase Gallery not generated on-site were created with it and Flux Q4 Dev model on a Machine with 8GB VRAM.
Show more

1K0 1 2 3 4 5 6 7 8 9K
6K0 1 2 3 4 5 6 7 8 9K
43.7K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

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.
The Lora is trained MidJourney Images that use my "Personalised Style" + Sketches and Illustration in a style dominated by different shades of Azure.
Works without the trigger words ArsMJStyle, AzureSketch, but gives stronger results with them.
Works great in the 0.3 - 1.5 range, depending on the Lora Stack you use.
I recommend starting in the 0.8 - 1.2 range


