Verified: 3 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.
Please upload some pics if you make anything worth seeing!
Work in progress!
I need to re-train a model on the same dataset, but upscaled as the current images are pretty low resolution and I think that makes the model anatomically confused...
Portraits look great for the most part, but scenes with people tend to break down more easily.
This as well as higher resolution gens is something I'll be working on for the next version. :)
Usage:
I personally use 40 steps, Flux guidance at 4-5, Euler, Flux2Scheduler.
1024x1024/1024x768/1080x810 are the resolutions I've been using.