Sign In

Robif-i (Flux1.d)

155

Download

1 variant available

SafeTensor

75.7 MB

Verified:

Type
LoRA
Stats

529

155

638

Reviews
Published

Oct 14, 2024

Base Model

Flux.1 D

Training
Steps: 7,000
Epochs: 10
Usage Tips
Strength: 1
Hash
AutoV2
8E94A244FF
Trigger Words
rbfi
default creator card background decoration
Followers - 44

44

Likes - 174

174

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 Cover.jpg

First released LoRA for "robotifying".

Trained on 70 Stable Cascade images.

Recommended strength settings: 0.0 - ~1.3 - 1.7 (s. Strength Comparison Chart (download for 14k res.))

The training happened along a triggerword "rbfi", 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.

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

All images were captioned with "rbfi" only.

Being one of the first test-trainings having turned into a spontaneous release idea afterwards,
there is room for improvement like variety of perspectives/colours/motifs/arrangements/etc.,
reason I at least feel like going for a v2.0 eventually.