Updated: Aug 24, 2024
styleVerified: a year ago
SafeTensor
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.
World of Warcraft classic style, V2 because V1 wasn't consistent enough
105 images, 15 epochs, 7 repeats.
Works best if you describe it as "An in-game screenshot from world of warcraft" followed by your prompt.
Example images from me are all:
Euler - Simple
25 steps
Q8_0.gguf
Q8_0 t5xxl
clip_l
cfg 1.0
guidance 3.5
I used Joycaption to get a base caption and manually checked and modified each one, then trained in flux on site trainer at 15 epochs, 7 repeats and 1024 size. Didn't change anything else.