Instructions to use miaaiart/superstar-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use miaaiart/superstar-2 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("miaaiart/superstar-2") prompt = "superstar, This is a photograph of a miaohwx woman with short black hair and fair skin, wearing a frilly, pink dress with puffed sleeves, holding a microphone. The lighting is soft and warm, creating a gentle glow. The camera angle is slightly low, emphasizing her serene expression. The background is blurred, keeping the focus on her. Film grain add vintage and dreamy effect to the image." image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Superstar 2
A Flux LoRA trained on a local computer with Fluxgym

- Prompt
- superstar, This is a photograph of a miaohwx woman with short black hair and fair skin, wearing a frilly, pink dress with puffed sleeves, holding a microphone. The lighting is soft and warm, creating a gentle glow. The camera angle is slightly low, emphasizing her serene expression. The background is blurred, keeping the focus on her. Film grain add vintage and dreamy effect to the image.
Trigger words
You should use superstar to trigger the image generation.
Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, Forge, etc.
Weights for this model are available in Safetensors format.
- Downloads last month
- -
Model tree for miaaiart/superstar-2
Base model
black-forest-labs/FLUX.1-dev