Download
1 variant available
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.
A review/like/follow helps keep me motivated! I'd love to see what you create and hear your feedback! ೕ(•̤̀ᵕ•̤́๑)ᵒᵏᵎᵎᵎᵎ
Mixtape Maximalism – a visual aesthetic rooted in the chaotic, unapologetically loud design sensibilities of '90s to early 2000s hip-hop mixtape and bootleg album covers, with a strong influence from No Limit Records' iconic album art. The goal of this LoRA is to reproduce that distinctive over-the-top style with questionable editing, where design restraint is nonexistent and everything competes for your attention.
Usage Tips
Weight: 0.7-1
Trigger:
mixtape maximalism styleI generally start the prompt with
An album cover in a mixtape maximalism style., followed by details about the main subject(s), then the text, and finally the background/any other misc elementsFeel free to experiment, but the source image text elements were captioned in the format:
The artist name "NAME" is written [position] in a [font] with [style/effect(s)], andThe album title "TITLE" ...E.g.,
The artist name "Oaky" is written across the top in a bold sans-serif font with a molten gold texture fill, a thin black stroke, a white glow, and lens flare effects.
Text effect triggers: fill, stroke, drop shadow, glow, 3d, beveled, embossed
Misc triggers:
lens flare effect(they'll probably show up anyway, but if you want more...)Use
A parental advisory label is positioned [position]if you'd like to include a parental advisory labelE.g.,
A parental advisory label is positioned in the bottom right corner
Notes
The LoRA captures the overall style I was aiming for, but text style/effect adherence isn't consistent at all. Looking to improve this in v2.
Showcases images have been upscaled by 1.5 with 0.15-0.2 denoising
Training Info
Images: 19
Steps: 3000
Network Rank/Alpha: 32
Learning Rate: 1e-4
Tool: ai-toolkit
Captioning: Florence-2-large-PromptGen v1.5, Claude 3.7, manual editing
