I felt like the V1 was a hit or miss. It didn't grasp the concept well enough.
So I started from scratch!
Introducing the new and improved BLOODY FLUX featuring an all new training dataset consisting of carefully selected high res images depicting bloody violence in an assortment of different ways. The captions are more detailed and contains both booru tags and natural language styles. No trigger word this time.
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 flux LoRA was created to allow the user to have more control over blood when generating realistic violence. The dataset consisted of 31 high resolution movie stills captioned in natural language.