Verified: 9 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.
POLADROIDS have sneakily arrived :-)
The effect they bring along is basically a retro-sci-fi-polaroid-often-vignetted/miniature-look including a bit of weirdness o.0
Trained on 27 Cascade images.
Recommended strength settings: 0.0 - ~2.0 (s. Strength Comparison Chart)
The training happened along a triggerword "pldrds", yet works as well without.
Without the triggerword the LoRA incorporates more like a photo filter/LUT when used along prompting.
For the miniature and also enhanced transformation look use of the triggerword is recommended with a strength setting of around 1.1. In relation to the prompt it´s being implemented along, settings could be higher and the triggerword could be repeated.
Lower strengths than 1.0 can create quite interesting coating mixtures.
The lower range is as well where style tinting usually happens without changing the motif toooo much.
TIPS: Play with Guidance around 2.0-3.5. Combine with Input Images.
All images were captioned with "pldrds" only.
Having as well been one of the very first trainings done here, the LoRA´s variety of motifs/perspectives/colours/etc. could still be improved along a greater amount of training images.
Reason I´m potentially going for a v2.