Pinkstack commited on
Commit
0bb6a19
·
verified ·
1 Parent(s): 811af3c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
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 crown, 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,
 
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,