Text-to-Image
Diffusers
Safetensors
English
PixelArtDiTPipeline
pixel-art
diffusion
flow-matching
diffusion-transformer
sprites
16x16
32x32
64x64
Instructions to use Pinkstack/LiliPixel-V1-190M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Pinkstack/LiliPixel-V1-190M with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Pinkstack/LiliPixel-V1-190M", dtype=torch.bfloat16, device_map="cuda") 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
|
@@ -27,7 +27,7 @@ language:
|
|
| 27 |
|
| 28 |
This model release is a from-scratch open weight text-to-pixel-art diffusion transformer (191M trainable parameters) that generates pixel "art"/sprite style images at native 16x16, 32x32 or 64x64 resolution. (64 pixel res also has realism toggle)
|
| 29 |
Caption tokens and image tokens share one sequence with full self-attention (single-stream DiT). Text is encoded by a frozen
|
| 30 |
-
[MongoDB/voyage-4-nano](https://huggingface.co/MongoDB/voyage-4-nano) (~346M parameters, not included in the weights, downloaded automatically on first use).
|
| 31 |
|
| 32 |
## Model details
|
| 33 |
|
|
@@ -61,12 +61,12 @@ from diffusers import DiffusionPipeline
|
|
| 61 |
pipe = DiffusionPipeline.from_pretrained(
|
| 62 |
"Pinkstack/LiliPixel-V1-190M",
|
| 63 |
custom_pipeline="Pinkstack/LiliPixel-V1-190M",
|
| 64 |
-
trust_remote_code=True,
|
| 65 |
torch_dtype=torch.bfloat16,
|
| 66 |
).to("cuda")
|
| 67 |
|
| 68 |
image = pipe(
|
| 69 |
-
prompt="cute border collie dog with a purple
|
| 70 |
height=32, width=32, # 16, 32 or 64
|
| 71 |
num_inference_steps=30, # 50 for 64 pixel images, 30 is quicker but may look worse
|
| 72 |
guidance_scale=3.0,
|
|
|
|
| 27 |
|
| 28 |
This model release is a from-scratch open weight text-to-pixel-art diffusion transformer (191M trainable parameters) that generates pixel "art"/sprite style images at native 16x16, 32x32 or 64x64 resolution. (64 pixel res also has realism toggle)
|
| 29 |
Caption tokens and image tokens share one sequence with full self-attention (single-stream DiT). Text is encoded by a frozen
|
| 30 |
+
[MongoDB/voyage-4-nano](https://huggingface.co/MongoDB/voyage-4-nano) (~346M parameters, not included in the weights, downloaded automatically on first use). The model needs roughly just 1GB of memory with lossless BF16 inference.
|
| 31 |
|
| 32 |
## Model details
|
| 33 |
|
|
|
|
| 61 |
pipe = DiffusionPipeline.from_pretrained(
|
| 62 |
"Pinkstack/LiliPixel-V1-190M",
|
| 63 |
custom_pipeline="Pinkstack/LiliPixel-V1-190M",
|
| 64 |
+
trust_remote_code=True, # must be true
|
| 65 |
torch_dtype=torch.bfloat16,
|
| 66 |
).to("cuda")
|
| 67 |
|
| 68 |
image = pipe(
|
| 69 |
+
prompt="cute border collie dog with a purple colar, transparent background", # end the prompt with ", transparent background" for 16,32 pixel sprites, start it with "realistic photo, " for realism images at 64x64.
|
| 70 |
height=32, width=32, # 16, 32 or 64
|
| 71 |
num_inference_steps=30, # 50 for 64 pixel images, 30 is quicker but may look worse
|
| 72 |
guidance_scale=3.0,
|