CRAFTJAI
Collection
AI-driven mood character generation from journal entries. This collection includes a labeled dataset and a fine-tuned LoRA model. • 2 items • Updated
How to use krprmf/CRAFTJAI-MoodGen-LoRA with Diffusers:
pip install -U diffusers transformers accelerate
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("krprmf/CRAFTJAI-MoodGen-LoRA")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]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("krprmf/CRAFTJAI-MoodGen-LoRA")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]CRAFTJAI-MoodGen-LoRA is a fine-tuned LoRA model based on FLUX.1-dev, designed for generating mood-specific characters from journal entries. The model enhances emotional alignment, style consistency, and personalization by leveraging AI-driven text-to-image generation. It supports eight primary moods derived from Plutchik’s Wheel of Emotions: joy, trust, fear, surprise, sadness, disgust, anger, and anticipation.
Weights for this model are available in Safetensors format.
Training was done using fal.ai/models/fal-ai/flux-lora-fast-training.
Base model
black-forest-labs/FLUX.1-dev