Instructions to use GGUFGuy/roblox-blocky-or-style with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use GGUFGuy/roblox-blocky-or-style with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Comfy-Org/stable-diffusion-v1-5-archive", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("GGUFGuy/roblox-blocky-or-style") prompt = "best quality, masterpiece, 1girl, solo, yaemikodef, white background, medium breasts, standing, full body, chibi, <lora:ROBLOXBlockyStyle:1>, <lora:yaemiko1:0.9>" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
ROBLOX Blocky | Style

- Prompt
- best quality, masterpiece, 1girl, solo, yaemikodef, white background, medium breasts, standing, full body, chibi, <lora:ROBLOXBlockyStyle:1>, <lora:yaemiko1:0.9>
- Negative Prompt
- aid210, badhandv4

- Prompt
- best quality, masterpiece, 1girl, solo, halo, animal ears, animal ear fluff, grey hair, medium hair, hair ornament, blue eyes, mismatched pupils, white shirt, scarf, jacket, skirt, long sleeves, necktie, open jacket, id card, standing, full body, white background, chibi, <lora:ROBLOXBlockyStyle:0.8>, <lora:ShirokoBA:0.9>
- Negative Prompt
- aid210, badhandv4
Model description
Recommend weights around 0.7-1
Best weight for me is 0.8
Clip Skip: 2
Recommend to use one of my prompt on the images i generated
Reuploaded to Hugging Face by GGUFGuy
CREDITS TO THE OWNER OF THE MODEL (Y_X) AND RUNWAYML
Original model link: https://civitai.com/models/197863/roblox-blocky-or-style
Trigger words
You should use chibi to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 7
Model tree for GGUFGuy/roblox-blocky-or-style
Base model
runwayml/stable-diffusion-v1-5 Finetuned
Comfy-Org/stable-diffusion-v1-5-archive