| --- |
| license: wtfpl |
| base_model: black-forest-labs/FLUX.1-dev |
| pipeline_tag: text-to-image |
| tags: |
| - text-to-image |
| - lora |
| - diffusers |
| - flux |
| - stationthis |
| library_name: diffusers |
| --- |
| |
| # nerfmodel |
|
|
| This LoRA captures the distinctive surreal and fantasy visual style of nerfmodel art, showcasing vivid colors and imaginative landscapes. The model excels in generating scenes featuring lone figures in striking environments, such as a barren yellow-orange desert with hints of green vegetation, all while incorporating intricate details like medieval armor and plumes. |
|
|
| **Trigger word:** `nerfmodel` |
|
|
| ## Sample Outputs |
|
|
| | | | |
| |:---:|:---:| |
| |  |  | |
| | *This is a digital drawing in a surreal, fantasy style, remin...* | *This is a digital drawing in a surreal, abstract nerfmodel s...* | |
| |  |  | |
| | *This is a digital drawing in a vibrant, abstract nerfmodel s...* | *This is a digital abstract painting with a dark green backgr...* | |
|
|
| ## Usage |
|
|
| ### ComfyUI |
|
|
| 1. Download the `.safetensors` file from the Files tab |
| 2. Place in `ComfyUI/models/loras/` |
| 3. Use the **Load LoRA** node with strength `0.8-1.0` |
| 4. Include `nerfmodel` in your prompt |
|
|
| ### Diffusers |
|
|
| ```python |
| import torch |
| from diffusers import FluxPipeline |
| |
| pipe = FluxPipeline.from_pretrained( |
| "black-forest-labs/FLUX.1-dev", |
| torch_dtype=torch.bfloat16 |
| ) |
| pipe.load_lora_weights("ms2stationthis/nerfmodel") |
| pipe.to("cuda") |
| |
| image = pipe( |
| prompt="nerfmodel portrait, soft lighting, detailed", |
| guidance_scale=3.5-4.0, |
| num_inference_steps=20-30, |
| generator=torch.Generator("cuda").manual_seed(42) |
| ).images[0] |
| |
| image.save("output.png") |
| ``` |
|
|
| ## Recommended Settings |
|
|
| | Parameter | Value | |
| |-----------|-------| |
| | LoRA Strength | 0.8-1.0 | |
| | Guidance Scale | 3.5-4.0 | |
| | Inference Steps | 20-30 | |
| | Resolution | 1024x1024 | |
|
|
| ## Example Prompts |
|
|
| - `nerfmodel this is a digital drawing in a surreal` |
| - `nerfmodel fantasy style` |
| - `nerfmodel yellow-orange desert with sparse green vegetation` |
| - `nerfmodel including a helmet with a red plume` |
|
|
| ## Training Details |
|
|
| - **Base model:** black-forest-labs/FLUX.1-dev |
| - **Training steps:** 4000 |
| - **Trigger word:** `nerfmodel` |
| - **Network:** LoRA rank 32, alpha 32 |
| - **Optimizer:** adamw8bit, lr 1e-4 |
| - **Precision:** float16 |
| - **Resolution:** 512, 768, 1024 (multi-res bucketed) |
|
|
| ## About |
|
|
| Trained using [StationThis](https://miladystation2.net) — an AI creative platform powered by $MS2. Train your own LoRAs via [@stationthisbot](https://t.me/stationthisbot) on Telegram. |
|
|
| --- |
|
|
| <sub>Generated by StationThis Training Pipeline</sub> |
|
|
