Sign In

MUK Monsieur style (Flux dev test version)

49
513
54
20
Updated: Aug 18, 2024
styleanime2dartstylecute
Verified:
SafeTensor
Type
LoRA
Stats
513
54
Reviews
Published
Aug 18, 2024
Base Model
Flux.1 D
Training
Steps: 3,000
Usage Tips
Clip Skip: 1
Strength: 1
Hash
AutoV2
37D426FA9D
bakariso's Avatar
bakariso
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.

Better to use prompts with long sentences, workflow examples with prompts inside the images.

The best way to use it is probably load the main model weights in fp8_e4m3 precision, not any quant, just lower precision, since it was trained with this accuracy.