|
--- |
|
base_model: |
|
- stabilityai/stable-diffusion-3.5-medium |
|
tags: |
|
- art |
|
license: other |
|
license_name: stabilityai-ai-community |
|
license_link: LICENSE |
|
--- |
|
# Bokeh 3.5 Medium |
|
<div align="center"> |
|
<img src="show.jpg" alt="00205_" /> |
|
</div> |
|
|
|
Bokeh 3.5 Medium is based on **Stable Diffusion 3.5 Medium** as its foundation model, using a 5M high-resolution open-source dataset that underwent rigorous quality and **aesthetic screening** for post-training, ensuring **excellent image quality**, **high fidelity of natural images**, preservation of fine **details**, and enhanced **controllability**. |
|
|
|
This model is released under the Stability Community License. |
|
For more details, visit [Tensor.Art](https://tensor.art) or [TusiArt](https://tusiart.com) to explore additional resources and useful information. |
|
|
|
## Overview |
|
|
|
- Continued training on **SD3.5M**, utilizing carefully curated high-resolution training data to achieve excellent image quality. |
|
- Trained with mixed short/long natural language captions. |
|
- **Short Captions:** Focus on the core subject content of the image. |
|
- **Long Captions:** Provide broader descriptions of the scene environment and atmosphere. |
|
- **Recommended Resolutions:** |
|
`1920x1024`, `1728x1152`, `1152x1728`, `1280x1664`, `1440x1440` |
|
- Powerful customized **fine-tuning performance** that can be widely used for **downstream production tasks**. |
|
- Powerful customized **fine-tuning performance** that can be widely used for **downstream production tasks**. |
|
- Achieve **8~10step** image generation through strong distillation technology, with high-resolution images generated in just 5 seconds on a 3090-level GPU with some quality loss. You can use the [8steps lora](bokeh_8steps_turboX_lora.safetensors) with the base checkpoint or use the [8step checkpoint](bokeh_8steps_turboX.safetensors). |
|
|
|
## Advantages |
|
|
|
### 🖼️ High-Quality Image Generation |
|
- **State-of-the-art visual fidelity** with improved detail extraction and **aesthetic consistency**. |
|
- **Enhanced resolution support** up to **200W pixels**, ensuring highly detailed image outputs. |
|
- **Carefully curated dataset** ensures better composition, lighting, and overall artistic appeal. |
|
|
|
### 🎯 Powerful Custom Fine-Tuning |
|
- **Exceptional LoRA training support**, making it highly effective for: |
|
- Photography |
|
- 3D Rendering |
|
- Illustration |
|
- Concept Art |
|
|
|
### ⚡ Efficient Inference & Training |
|
- **Low hardware requirements for inference:** |
|
- **Medium model:** 9GB VRAM (without T5) |
|
- **Full weights inference:** 16GB VRAM (suitable for local deployment) |
|
- **LoRA fine-tuning VRAM requirement:** 12GB - 32GB |
|
|
|
## Known Issues |
|
|
|
- **Potential human anatomy inconsistencies.** |
|
- **Limited ability to generate photorealistic images.** |
|
- **Some concepts may suffer from aesthetic quality issues.** |
|
|
|
|
|
## Prompting Guide |
|
|
|
### Use a structured prompt combining: |
|
- **Main subject** (e.g., `"Close-up of a macaw"`) |
|
- **Detailed features** (e.g., `"vivid feathers, sharp beak"`) |
|
- **Background environment** (e.g., `"dimly lit environment"`) |
|
- **Atmospheric description** (e.g., `"soft warm lighting, cinematic mood"`) |
|
- **Optimal token length:** **30-70 tokens**. |
|
|
|
## Example Output |
|
Using diffusers： |
|
```python |
|
import torch |
|
from diffusers import StableDiffusion3Pipeline |
|
|
|
pipe = StableDiffusion3Pipeline.from_pretrained("tensorart/bokeh_3.5_medium", torch_dtype=torch.bfloat16) |
|
pipe = pipe.to("cuda") |
|
|
|
image = pipe( |
|
"Close-up of a macaw, dimly lit environment", |
|
num_inference_steps=28, |
|
guidance_scale=4, |
|
height=1920, |
|
width=1024, |
|
negative_prompt="anime,cartoon,bad hands,extra finger，blurred,text,watermark", |
|
negative_prompt_3="" |
|
).images[0] |
|
image.save("macaw.jpg") |
|
``` |
|
Using comfyui: |
|
To use this workflow in **ComfyUI**, download the JSON file and load it: |
|
|
|
[Base Model Workflow](bk_workflow.json) |
|
|
|
[8steps-TurboX Workflow](bokeh_turboX.json) |
|
|
|
### 🔧 Training Tools |
|
- **Kohya_ss:** [GitHub Repository](https://github.com/bmaltais/kohya_ss.git) |
|
- **Simple Tuner:** [GitHub Repository](https://github.com/bghira/SimpleTuner) |
|
|
|
## Contact |
|
* Website: https://tensor.art https://tusiart.com |
|
* Developed by: TensorArt |
|
*  |
|
|
|
|
|
|
