Skip to content

Instantly share code, notes, and snippets.

You are professional diffusion model prompt writer. There is a prompt in # PROMPT section. There is a prompt guidelines in # GUIDELINES section. Rewrite prompt following guidelines closely.
# GUIDELINES
Prompt Structure: The model was trained with tag-based captions and the tag-ordering method. Use this structured template: 1girl/1boy/1other, character name, from which ies, rating, everything else in any order and end with quality enhancement
The model supports various special tags that can be used to control different aspects of the image generation process. These tags are carefully weighted and tested to vide consistent results across different prompts. Booru tags can be also used.
Quality tags are fundamental controls that directly influence the overall image quality and detail level. Available quality tags: masterpiece, best quality, low quality
For Quality Enhancement Tags Add these tags at the end of your prompt: masterpiece, digital illustration
Temporal tags allow you to influence the artistic style
Prompt to rewrite natural-language prompt according to https://huggingface.co/cagliostrolab/animagine-xl-4.0 guidelines
===
You are professional diffusion model prompt writer. There is a prompt in # PROMPT section. There is a prompt guidelines in # GUIDELINES section. Rewrite prompt following guidelines closely.
# PROMPT
Anime-style digital illustration of two animated characters seated on identical red thrones. The character on the left appears to be male, with dark hair, fair skin, and is dressed in a red and yellow shirt, complemented by dark pants and shoes. He has his left elbow resting on his knee, indicating a relaxed posture. His right hand is lightly grasping the armrest of the throne, suggesting a confident demeanor. The character on the right appears to be female, with blonde hair, fair skin, and is wearing a maroon dress with a white collar. She has an attentive posture, with her hands resting comfortably on her legs. Her gaze is directed more towards the viewer, creating a sense of connection w
@IPv6
IPv6 / make_starling_atlas.py
Last active February 4, 2022 01:50
Starling Atlas generation. Recursively loads images from directory and arranges them into one big png file with xml decription
# Starling Atlas generation: make_starling_atlas.py
# Recursively loads images from directory and arranges them into one big png file with xml decription
# Reqirement: PIL
# ported from https://github.com/Gamua/Sparrow-Framework/blob/master/sparrow/util/atlas_generator/generate_atlas.rb
# ********* ************* *******
import sys
import os
from PIL import Image
local function clamp(value, low1, high1)
if value<low1 then
return low1
end
if value>high1 then
return high1
end
return value
end
def eliminateNG(self, node):
node_groups = bpy.data.node_groups
# Get the node group name as 3-tuple (base, separator, extension)
(base, sep, ext) = node.node_tree.name.rpartition('.')
# Replace the numeric duplicate
if ext.isnumeric():
if base in node_groups:
print("- Replace nodegroup '%s' with '%s'" % (node.node_tree.name, base))
def get_object_by_name(name):
if name in bpy.data.objects:
return bpy.data.objects[name]
return None
def unselect_all():
for obj in bpy.data.objects:
obj.select = False
def force_visible_object(obj):