santa hat
deerdeer nosedeer glow
Sign In

Semi Realism Anime

26
209
794
6
Updated: Aug 16, 2024
style
Verified:
SafeTensor
Type
LoRA
Stats
209
794
Reviews
Published
Aug 16, 2024
Base Model
Flux.1 D
Training
Steps: 1,163
Epochs: 5
Usage Tips
Clip Skip: 1
Trigger Words
FFAOR
Hash
AutoV2
606EC51528
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.

Okay, I have had enough time to experiment to write a better description of this model now. This model is trained on oil paintings with a hint of anime style to them. Its meant to be run at or below 0.8 strength. Its way over powered and will absolutely break things at higher strengths. Less is more with this one. I've found the lower CFG around 3.5-5 to give me the best results but feel free to experiment beyond that, sometimes going higher can give interesting colors.

Use the Trigger words FFAOR for full effects and I highly recommend being descriptive with your colors. Flux has better prompt adherence than other models and allows you to be more specific in your designs. Flowery language also seems a bit more acceptable to its prompts compared to SD.

This also mixes well with many other LoRAs when this one is used at a lower strength. I've personally found it to combine with my InkSketch Flux Lora in fun ways.