| Property | Value |
|---|---|
| Base Model | black-forest-labs/FLUX.1-dev |
| License | flux-1-dev-non-commercial-license |
| Language | English |
| Pipeline | Text-to-Image |
What is luna-NSFW?
luna-NSFW is a specialized LoRA (Low-Rank Adaptation) model trained on the FLUX.1-dev base model using Replicate's training infrastructure. It's designed for text-to-image generation with specific focus on the LUNA character style.
Implementation Details
The model is implemented using the diffusers library and requires the FLUX.1-dev base model. It supports CUDA acceleration and operates with float16 precision for optimal performance. Integration is straightforward using the AutoPipelineForText2Image pipeline.
- Built on FLUX.1-dev architecture
- Trained using Replicate's flux-dev-lora-trainer
- Requires 'LUNA' as trigger word for optimal results
- Supports LoRA weight customization
Core Capabilities
- Text-to-image generation with character-specific styling
- Compatible with diffusers pipeline
- Supports weight merging and fusing
- Float16 precision support for efficient processing
Frequently Asked Questions
Q: What makes this model unique?
This model specializes in generating images using the LUNA trigger word, offering a specific artistic style through LoRA adaptation of the FLUX.1-dev base model.
Q: What are the recommended use cases?
The model is ideal for generating character-specific artwork using the LUNA trigger word, particularly useful for artists and creators working with the FLUX ecosystem.