Verified: 10 months 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.
A lora in the style of the character portraits of Disco Elysium. Trained on 60 images of just the character portraits, no skill portraits or backgrounds.
No trigger words, just asking for an abstract portrait, abstract background, harsh brushstrokes, expressionism, seems to work.
V2 is out. I don't consider its necessarily better than V1, which you may find to be better, but I think the effect is a little stronger in V2 and a bit more consistent.
The full Dev model works much better than its cut down versions.