Sign In

smOOthie F1- Soft Shaded Style for FLUX

4

Updated: Dec 15, 2024

styleillustrationcartoonsoft

Download

1 variant available

SafeTensor

37.94 MB

Verified:

Type
LoRA
Stats

265

4

2

Reviews
Published

Oct 11, 2024

Base Model

Flux.1 D

Training
Steps: 1,500
Usage Tips
Clip Skip: 1
Strength: 1.1
Hash
AutoV2
A1EBC65E3B
default creator card background decoration
Likes - 15405

15.4K

Downloads - 122430

122.4K

Generations - 83105

83.1K

TheAlly's Granny Grippers!

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_00939_.png

smOOthie F1- Soft Shaded Style for FLUX

usage:

Weight can go from 0.7 to 2

It heavily depends on the prompt and how much you want the style to be visible. Also, cranking up the weight will lean onto a more flatter (but more stylized) style. Also also, mutation can happen if the weight is too high. Use higher values only on images that refuse to steer away from the photographic look.

You don't have to use terms such as "soft painterly" or "soft shading" or similar. The point of the lora was to avoid using the base illustration knowledge of FLUX (wich varies a lot in quality and style from prompt to prompt) and have a semi-consistent output for the style. So, you can use those terms in prompt, but they will stir the output and have unpredictable results.

If you like what I do donate some Buzz or buy me a coffee here

If you want to post an image made with this LoRa on civitAi, please, do not cross-post but create a new post on this page with the ( + add Post) button, it will help me gain buzz without the need to rely on tipping.