import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Jonjew/RoboticsFlux")
prompt = "CRVStyle"
image = pipe(prompt).images[0]RobotiCs FLUX
.jpeg)
- Prompt
- CRVStyle
Model description
FROM https://civitai.com/models/710766/robotics-flux?modelVersionId=795014
This is RobotiCs. RobotiCs is a high quality FLUX LORA that was trained on Flux-S (Schnell).
This LORA was based on Dervlex's CRVSTyle FLUX LORA for DEV (which was trained on CivitAI with Buzz) while this one was trained on RTX 3090 with experimental settings. Still trying you know. But... it works.
Instructions & Recommendations:
The trigger word is "CRVStyle" (Steps recommended from 4 onwards and my preferred are 7 or 8 steps). Also put the trigger word first to more powered effect.
You can power up the style with semanthics related to robots, cyborgs, etc.
Strenght of the LORA should be 0.75 onwards and depending if the concept you want is not there, boost it more!
See ya!
PS: This LORA has an alternative version in our Patreon so it you like my content, please support me and my partner for more quality goodies. Thanks!
Trigger words
You should use CRVStyle to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 4
Model tree for Jonjew/RoboticsFlux
Base model
black-forest-labs/FLUX.1-dev