Stillsuit [Flux] [SDXL]
(CivitAI)
Model description
v1.33
This version is the first attempt at a stillsuit with Flux. It comes out to be more 'stillsuit(ish)'. However, it works very well with the online generators. Offline though, it seems to be more 'ish'... (makes me scratch my head).
V1.32
This version continues to improve quality, and give more consistent results. In testing with a lora strength of .6 it has seemed pretty easy to get images with a good stillsuit. This version has no masks. It will also do children pretty well. Trained resolutions 832x1216 mostly.
V1.31
The stillsuit's are much higher quality in this version, and take color much easier. Has better male resources. withoutmask prompt has been removed (it is in this version, but doesn't work. I plan to remove it in future versions).
Suggested positive prompt: human head, natural skin
Suggested negative prompt: long torso, long neck,
v1.3
This version finally brings withmask and withoutmask prompts. This model still needs a lot more images to train on, and is a WIP.
v1.21
It should have a sharper stillsuit, and the abdomen should be more consistent. It was also trained without cloaks. Using stillsuit with tattered cloak works pretty well if you want to add a cloak. Mask up and mask down will, hopefully, be worked out in future versions. For now, it is just luck of the draw.
v1.1
This is trained with 2 triggers, stillsuit mask up, and stillsuit mask down. Use either prompt, and expect erratic results because you could get either version, but more than likely you'll get mask up. The quality was a big enough improvement, so I am publishing it while I figure out how to improve the reliability of mask up/down.
v1.0
Lora of a Dune Stillsuit. The second version of this, v1.0, has quite a bit better quality than the first, but still needs some improvement. Keyword is stillsuit. Be gentle, this is my first time training.
Trigger words
You should use stillsuit
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Use it with the 🧨 diffusers library
from diffusers import AutoPipelineForText2Image
import torch
device = "cuda" if torch.cuda.is_available() else "cpu"
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('Keltezaa/stillsuit-flux-sdxl', weight_name='stillsuit_v133.safetensors')
image = pipeline('This digital artwork depicts a futuristic, sci-fi scene. The subject is a woman standing in a vast, a rock outcropping in a sandy desert landscape under a cloudless sky at nigh noon. The woman is dressed in a stillsuit from the Dune universe, in shades of brown and beige, with high-tech, sleek lines and a mask that hangs around her neck and nose piece on. She has a stern, focused expression and is wearing gloves, knee pads, and shin guards, suggesting a survival suit. The sand dunes in the background have intricate, rippled patterns, enhancing the barren, inhospitable environment. The overall color palette is dominated by earthy tones, from the woman's suit to the sand, blending seamlessly with an almost ethereal glow of the sky, which adds a surreal, otherworldly atmosphere. The artwork captures a sense of isolation and the harshness of an extraterrestrial desert environment. , , , perfection style v3,, aidmaimageupgrader, max details, ').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers
- Downloads last month
- 13
Model tree for Keltezaa/stillsuit-flux-sdxl
Base model
black-forest-labs/FLUX.1-dev