When using with my others Beta models, adjust the weight to 0.60 (to either one) if not it will generate grid images (caused by the training images)
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.
V3 beta, (more like a 2.5) but better.
(Recommended Read)
Improvements v3 over v2:
- More inclined to touch indicated parts
- lil Better anatomy
- Improved by a lil self touching
- Better shots from behind
- Better camera angles control
*old:This model is intended to improve the physical interactions between people*
For v2: recommended 0.9 but works well in lower or higher
Recommendations for v3:
-- If used with other of my beta models, lower the weight of either one to 0.60( if not, tends to do grid images, dataset issues)
-- "The man hides in front of her" is present in the dataset, so you can use that
.jpeg)