Instructions to use miragenotsigspamming/annalie with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use miragenotsigspamming/annalie 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("miragenotsigspamming/annalie") prompt = "\"25-year-old American-European woman, light skin, oval-heart face, bright blue eyes, straight nose, dark blonde shoulder-length hair, natural lighting, photorealistic, high detail, front and side face views, studio portrait --v 6 --style raw\"" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
annalie

- Prompt
- "25-year-old American-European woman, light skin, oval-heart face, bright blue eyes, straight nose, dark blonde shoulder-length hair, natural lighting, photorealistic, high detail, front and side face views, studio portrait --v 6 --style raw"
Model description
๐ฆ Model Card: annalie_0006 Trained with: Ostris AI Toolkit Base Model: FLUX (e.g., black-forest-labs/FLUX.1-dev or FLUX.1-schnell) Format: .safetensors (LoRA) File: annalie_0006.safetensors ๐งโ๐จ Description This LoRA fine-tunes the FLUX diffusion model to generate consistent portraits of a fictional character named Annalie, embodying the following traits: Ethnicity: White (American-European) Age: ~25 years old Skin tone: Light Face shape: Oval-heart hybrid Eye color: Blue Nose: Straight Hair: Dark blonde, natural styling The model was trained using high-quality, synthetically generated reference images to ensure ethical compliance and stylistic consistency. It works best when used with descriptive prompts that align with the learned features. โ๏ธ Usage Compatible with: ComfyUI (with FLUX support + LoRA loader) Diffusers (via Ostris adapter if needed huggingface.co ) Other UIs supporting .safetensors LoRAs on FLUX backbones Recommended prompt structure: 1 annalie_0006, 25-year-old european woman, light skin, blue eyes, dark blonde hair, heart-shaped face, soft natural lighting, photorealistic portrait Adjust weight between 0.6โ1.0 depending on desired fidelity vs. creativity. ๐ ๏ธ Training Details Toolkit: Ostris AI Toolkit GitHub Base Checkpoint: FLUX.1 (specify dev or schnell if known) Dataset: Custom-generated synthetic images matching target appearance Resolution: Likely 512x512 or 768x768 (standard for FLUX LoRAs www.runcomfy.com ) Epochs / Steps: (Optional: fill in if you have logs) ๐ This model represents a fictional character and does not depict any real person. Training data was ethically sourced/generated.
Trigger words
You should use annalie to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 7
Model tree for miragenotsigspamming/annalie
Base model
black-forest-labs/FLUX.1-dev