|
|
--- |
|
|
language: |
|
|
- en |
|
|
license: other |
|
|
license_name: pixelscribe-non-commercial-license |
|
|
license_link: LICENSE.md |
|
|
tags: |
|
|
- text-to-image |
|
|
- image-generation |
|
|
- Diffusers |
|
|
- PixelScribe |
|
|
- flux |
|
|
base_model: |
|
|
- sbapan41/PixelScribe |
|
|
new_version: sbapan41/PixelScribe |
|
|
pipeline_tag: text-to-image |
|
|
library_name: diffusers |
|
|
--- |
|
|
<div align="center"> |
|
|
<img src="https://huggingface.co/datasets/Quantamhash/Assets/resolve/main/images/dark_logo.png" |
|
|
alt="Title card" |
|
|
style="width: 500px; |
|
|
height: auto; |
|
|
object-position: center top;"> |
|
|
</div> |
|
|
|
|
|
`PixelScribe` is a 12. billion parameter rectified flow transformer capable of generating images from text descriptions. |
|
|
|
|
|
# Key Features |
|
|
1. Cutting-edge output quality, second only to our state-of-the-art model `PixelScribe`. |
|
|
2. Competitive prompt following, matching the performance of closed source alternatives . |
|
|
3. Trained using guidance distillation, making `PixelScribe` more efficient. |
|
|
4. Open weights to drive new scientific research, and empower artists to develop innovative workflows. |
|
|
5. Generated outputs can be used for personal, scientific, and commercial purposes as described |
|
|
|
|
|
# Usage |
|
|
We provide a reference implementation of `PixelScribe`, as well as sampling code, in a dedicated [github repository](https://github.com/MotoBwi/PixelScribe.git). |
|
|
Developers and creatives looking to build on top of `PixelScribe` are encouraged to use this as a starting point. |
|
|
|
|
|
|
|
|
## Diffusers |
|
|
|
|
|
To use `PixelScribe` with the 🧨 diffusers python library, first install or upgrade diffusers |
|
|
|
|
|
```shell |
|
|
pip install -U diffusers |
|
|
``` |
|
|
|
|
|
Then you can use `FluxPipeline` to run the model |
|
|
|
|
|
```python |
|
|
import torch |
|
|
from diffusers import FluxPipeline |
|
|
|
|
|
pipe = FluxPipeline.from_pretrained("sbapan41/PixelScribe", torch_dtype=torch.bfloat16) |
|
|
pipe.enable_model_cpu_offload() #save some VRAM by offloading the model to CPU. Remove this if you have enough GPU power |
|
|
|
|
|
prompt = "A cat holding a sign that says hello world" |
|
|
image = pipe( |
|
|
prompt, |
|
|
height=1024, |
|
|
width=1024, |
|
|
guidance_scale=3.5, |
|
|
num_inference_steps=50, |
|
|
max_sequence_length=512, |
|
|
generator=torch.Generator("cpu").manual_seed(0) |
|
|
).images[0] |
|
|
image.save("PixelScribe.png") |
|
|
``` |
|
|
|
|
|
|
|
|
|
|
|
--- |
|
|
# Limitations |
|
|
- This model is not intended or able to provide factual information. |
|
|
- As a statistical model this checkpoint might amplify existing societal biases. |
|
|
- The model may fail to generate output that matches the prompts. |
|
|
- Prompt following is heavily influenced by the prompting-style. |
|
|
|
|
|
# Out-of-Scope Use |
|
|
The model and its derivatives may not be used |
|
|
|
|
|
- In any way that violates any applicable national, federal, state, local or international law or regulation. |
|
|
- For the purpose of exploiting, harming or attempting to exploit or harm minors in any way; including but not limited to the solicitation, creation, acquisition, or dissemination of child exploitative content. |
|
|
- To generate or disseminate verifiably false information and/or content with the purpose of harming others. |
|
|
- To generate or disseminate personal identifiable information that can be used to harm an individual. |
|
|
- To harass, abuse, threaten, stalk, or bully individuals or groups of individuals. |
|
|
- To create non-consensual nudity or illegal pornographic content. |
|
|
- For fully automated decision making that adversely impacts an individual's legal rights or otherwise creates or modifies a binding, enforceable obligation. |
|
|
- Generating or facilitating large-scale disinformation campaigns. |
|
|
|
|
|
# License |
|
|
This model falls under the [`PixelScribe` Non-Commercial License]. |
