Download
2 variants available
SafeTensor
Neon_Cyberpunk_Detailer_FLUX_multi_trigger.safetensors
Verified: 2 years ago
Other Formats
Neon_Cyberpunk_Detailer_FLUX_single_trigger.zip
Verified: 2 years ago
8010 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
8270 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
1.5K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
(111)
Sep 15, 2024
The LoRA was trained on Flux-Dev.
It also works with Flux-Schnell, but I behaves slightly differently.
The showcase images are made with Flux-Dev.
For Flux Dev I recommend the following setting - Lora strength 0.6 - 1.0 greatly depending on the image, highres fix with denoising 0.4
Additional Trigger: slums, alley, hologram, holographic, advertisement, neon sign, futuristic clothes, cyberarm, cyberleg, cybernetics implants, etc.
Show more


5.3K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
13.6K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
116.2K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

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.
Hey there,
I personally think that the Flux base checkpoint lacks in regards of cyberpunk scenery, so I tried something new and train a detailer LoRA that covers most of these shortcoming. I probably spend 30h on training data and evaluation of the various iterations.
In the end I have decided to upload two versions of the final iteration of the LoRA. One is using only a single trigger word for the effect. The other one used tags in addition to the trigger word to overwrite certain concept and thus should give you more control over the composition.
I personally prefer the multit-trigger over the single-trigger version, but you have both under the same download and can choose either one. (I had to zip one of them to be able to upload both)
If you enjoy my work, consider showing your support with a 👍 or ❤️ on the model or images—it really keeps me motivated!
You can also follow me or buy me a coffee ☕ at: https://ko-fi.com/madcaddie
Usage tips for the LoRA are in the version details
Thanks and have fun!
