Sign In
home
models
images
videos
posts
articles
bounties
tools
challenges
events
shop

Robif-i-N (Flux1.d)

32
161
125
18
Updated: Nov 14, 2024
styleandroidscifirobotslorastyle lora
Verified:
SafeTensor
Type
LoRA
Stats
161
125
601
Reviews
(32)
Published
Nov 11, 2024
Base Model
Flux.1 D
Training
Steps: 8,400
Epochs: 10
Usage Tips
Strength: 1.1
Trigger Words
rbfin
Hash
AutoV2
5869F6A8BA
default creator card background decoration
Moofi
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.

Robif-i-N(octron) is basically a variant of Robif-i, still varying enough for an individual release. Darker, less complex, yet that for cleaner.


Compared to Robif-i, the portion of mech/robot training images had been reduced and gave room for an androidic touch plus sculptures and objects. The training set was an already existing series of images generated a while ago, around the time of, yet prior to Robif-i´s images.
All training images had been manually shape-edited in Photoshop before training.


Oh, and a lot of clouds appear :-D

Trained on 84 Stable Cascade images.

Recommended strength settings: 0.0 - ~2.1 (s. Strength Comparison Chart (download for 14k res.))

TIPS: Play with Guidance around 2.0-3.5. Combine with Input Images.

The training happened along a triggerword "rbfin", yet works as well without.

Still, using the triggerword increases the influence and also results in interesting styles within the lower influence strength range, like can be seen on the Strength Comparison Chart.

All images were captioned with "rbfin" only.