Instructions to use jamproduction25/Jalisa_Avari_V7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use jamproduction25/Jalisa_Avari_V7 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("jamproduction25/Jalisa_Avari_V7") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Jalisa_Avari_V7 (Ultra)
This is a LoRA trained on FLUX.1-dev for generating images of Jalisa Avari.
Model Details
- Trained by: jamproduction25
- Architecture: Flux-1-dev / LoRA
- Training Steps: 1824
- Epochs: 18
- Resolution: 1024x1024
- Optimizer: Prodigy
Trigger Words
To activate this model, use the following phrase in your prompt:
a photo of Jalisa_Avari
Usage
Recommended Settings
- Inference Steps: 20-30
- Guidance Scale: 3.5 (Standard for Flux)
- LoRA Weight: 0.7 - 1.0 (Adjust based on how strong you want the likeness)
Example Prompt
a photo of Jalisa_Avari standing in a neon-lit city street at night, cinematic lighting, high detail, 4k
Training Dataset
This model was trained on 38 high-quality images with 3 repeats each, totaling 114 training images per epoch.
License
This model is a derivative of FLUX.1-dev and is subject to the FLUX.1-dev Non-Commercial License.
- Downloads last month
- 1
Model tree for jamproduction25/Jalisa_Avari_V7
Base model
black-forest-labs/FLUX.1-dev