Instructions to use madtune/pixeldit-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use madtune/pixeldit-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("nvidia/PixelDiT-1300M-1024px", torch_dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("madtune/pixeldit-diffusers") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -24,17 +24,6 @@ All credit for the model architecture and weights goes to NVIDIA Research. This
|
|
| 24 |
|
| 25 |
---
|
| 26 |
|
| 27 |
-
## Gallery — IP-Adapter style transfer (SigLIP only, no text prompt)
|
| 28 |
-
|
| 29 |
-
| | | | | |
|
| 30 |
-
|---|---|---|---|---|
|
| 31 |
-
|  |  |  |  |  |
|
| 32 |
-
|  |  |  |  |  |
|
| 33 |
-
|
| 34 |
-
> All generated with [`madtune/pixeldit-controlnet`](https://huggingface.co/madtune/pixeldit-controlnet) — IP-Adapter only, zero text conditioning.
|
| 35 |
-
|
| 36 |
-
---
|
| 37 |
-
|
| 38 |
## What is PixelDiT?
|
| 39 |
|
| 40 |
PixelDiT is a 1.3B parameter **pixel-space** diffusion transformer — no VAE, generates images directly in pixel space. Runs on **4GB VRAM**.
|
|
|
|
| 24 |
|
| 25 |
---
|
| 26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
## What is PixelDiT?
|
| 28 |
|
| 29 |
PixelDiT is a 1.3B parameter **pixel-space** diffusion transformer — no VAE, generates images directly in pixel space. Runs on **4GB VRAM**.
|