Commit ·
4d2f977
verified ·
0
Parent(s):
initial commit
Browse files- .gitattributes +55 -0
- README.md +111 -0
.gitattributes
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.lz4 filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
# Audio files - uncompressed
|
| 38 |
+
*.pcm filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
*.sam filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
*.raw filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
# Audio files - compressed
|
| 42 |
+
*.aac filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
*.flac filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
*.mp3 filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
*.ogg filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
*.wav filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
# Image files - uncompressed
|
| 48 |
+
*.bmp filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
*.gif filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
*.png filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
*.tiff filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
# Image files - compressed
|
| 53 |
+
*.jpg filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
*.jpeg filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
*.webp filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- text-to-image
|
| 4 |
+
- lora
|
| 5 |
+
- diffusers
|
| 6 |
+
- template:diffusion-lora
|
| 7 |
+
widget:
|
| 8 |
+
- output:
|
| 9 |
+
url: images/knight.png
|
| 10 |
+
text: >-
|
| 11 |
+
A pixel art sprite of a medieval knight wearing metal armor and a helmet
|
| 12 |
+
with a red plume, a sword in one hand and a shield in the other hand. The
|
| 13 |
+
background is white.
|
| 14 |
+
- output:
|
| 15 |
+
url: images/witch.png
|
| 16 |
+
text: >-
|
| 17 |
+
A pixel art image of a witch with long red hair and blue eyes, wearing a
|
| 18 |
+
purple hat and robes trimmed with white and light purple colors. White
|
| 19 |
+
background
|
| 20 |
+
- output:
|
| 21 |
+
url: images/butler.png
|
| 22 |
+
text: >-
|
| 23 |
+
A pixel art image of a man with light brown hair in a long ponytail. He is
|
| 24 |
+
wearing a butler outfit and leaning forward towards the viewer holding a
|
| 25 |
+
bowl of soup. The background is a fancy restaurant with dining tables in the
|
| 26 |
+
back, a chandelier, and a painting of a noblewoman on the left walls.
|
| 27 |
+
- output:
|
| 28 |
+
url: images/island_base.png
|
| 29 |
+
text: >-
|
| 30 |
+
A pixel art aerial shot of an island in the middle of the ocean. On the
|
| 31 |
+
right side of the island is a giant metal orb building with a satellite on
|
| 32 |
+
top of it.
|
| 33 |
+
- output:
|
| 34 |
+
url: images/sand_dunes_tower.png
|
| 35 |
+
text: >-
|
| 36 |
+
A pixel art scene of wide, vast sand dunes with a tall cylindrical tower in
|
| 37 |
+
the far background surrounded by a sandstorm. In the foreground is a
|
| 38 |
+
medieval carriage being pulled by a triceratops moving towards the tower.
|
| 39 |
+
- output:
|
| 40 |
+
url: images/stairs_darkness_eyes.png
|
| 41 |
+
text: >-
|
| 42 |
+
A pixel art image of a top-down view of stairs leading down into darkness.
|
| 43 |
+
In the background the darkness has several faint red eyes.
|
| 44 |
+
- output:
|
| 45 |
+
url: images/ddagger_grid.png
|
| 46 |
+
text: >-
|
| 47 |
+
A pixel art sprite of a short red dagger with a green poisoned tip on the
|
| 48 |
+
top right and a gray and brown hilt. There are 16 copies of the sprite in a
|
| 49 |
+
4 by 4 grid. The background is white.
|
| 50 |
+
- output:
|
| 51 |
+
url: images/dshield.png
|
| 52 |
+
text: >-
|
| 53 |
+
A pixel art sprite of a rectangular orange shield with the head of a gray
|
| 54 |
+
dragon with its mouth open facing straight. The background is white.
|
| 55 |
+
- output:
|
| 56 |
+
url: images/skeleton_sprite.png
|
| 57 |
+
text: >-
|
| 58 |
+
A pixel art sprite of a skeleton warrior wearing a helmet with two horns,
|
| 59 |
+
holding an axe with both hands raised, facing right, white background
|
| 60 |
+
base_model: baidu/ERNIE-Image
|
| 61 |
+
instance_prompt: null
|
| 62 |
+
license: apache-2.0
|
| 63 |
+
---
|
| 64 |
+
# pixel_assets_general_ernie_v1
|
| 65 |
+
|
| 66 |
+
<Gallery />
|
| 67 |
+
|
| 68 |
+
## Model description
|
| 69 |
+
|
| 70 |
+
A pixel art LoRA for general-purpose game assets such as character sprites, creatures, items/equipment, backgrounds, scenery, and icons.
|
| 71 |
+
|
| 72 |
+
## How to use
|
| 73 |
+
|
| 74 |
+
You can use the default ERNIE-Image-Turbo workflow from ComfyUI, and no prompt enhancer needed. The sample images also have workflows.
|
| 75 |
+
|
| 76 |
+
## How to get pixel-perfect images
|
| 77 |
+
|
| 78 |
+
Downscale by a factor of 4. So 512x512 images should downscale to 128x128, 1024x1024 to 256x256, and so on. Using k-centroid with something like [PixelOE](https://github.com/KohakuBlueleaf/PixelOE) works well.
|
| 79 |
+
|
| 80 |
+
See examples below:
|
| 81 |
+
|
| 82 |
+
| Raw output | K-centroid downscaled, then upscaled back 4x|
|
| 83 |
+
| ------------- | ------------- |
|
| 84 |
+
|  |  |
|
| 85 |
+
|  |  |
|
| 86 |
+
|  |  |
|
| 87 |
+
|  |  |
|
| 88 |
+
|  |  |
|
| 89 |
+
|  | 
|
| 90 |
+
|  |  |
|
| 91 |
+
|  |  |
|
| 92 |
+
|  |  |
|
| 93 |
+
|
| 94 |
+
## Does this LoRA work with ERNIE-Image base?
|
| 95 |
+
|
| 96 |
+
Yes, but I don't recommend it. **The LoRA is meant to be used with the turbo model.** For some reason, outputs with the base model are very bad. The colors are way too bright or saturated, and there are more issues with anatomy. Maybe there's a problem with my settings.
|
| 97 |
+
|
| 98 |
+
## Notes & Issues
|
| 99 |
+
|
| 100 |
+
There are still some issues with certain prompts with the ERNIE turbo model.
|
| 101 |
+
- The model tends to make characters face forward or in a 3/4 angle even if your prompt has a different view. This might just be a limit of the turbo model, though.
|
| 102 |
+
- If prompting for sprites, make sure to include "white background" somewhere, otherwise you'll sometimes get a detailed background.
|
| 103 |
+
- Since I trained this on a 4x upscaled pixel art dataset, if you want smaller sprites, just prompt for copies of a sprite in a 2x2 or 4x4 grid (see the sample images).
|
| 104 |
+
- The dataset this LoRA was trained on contains 512x512, 768x768, and 1024x1024 images, but you can change the resolution and still get decent images.
|
| 105 |
+
|
| 106 |
+
|
| 107 |
+
|
| 108 |
+
## Download model
|
| 109 |
+
|
| 110 |
+
|
| 111 |
+
[Download](/svntax-dev/pixel_assets_general_ernie_v1/tree/main) them in the Files & versions tab.
|