Instructions to use AiArtLab/sdxs-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AiArtLab/sdxs-1b with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("AiArtLab/sdxs-1b", dtype=torch.bfloat16, device_map="cuda") prompt = "sdxs-1b" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
alpha
Browse files- README.md +2 -2
- media/boy.jpg +3 -0
- media/girl.jpg +2 -2
- media/result_grid.jpg +2 -2
- samples/unet_384x704_0.jpg +2 -2
- samples/unet_416x704_0.jpg +2 -2
- samples/unet_448x704_0.jpg +2 -2
- samples/unet_480x704_0.jpg +2 -2
- samples/unet_512x704_0.jpg +2 -2
- samples/unet_544x704_0.jpg +2 -2
- samples/unet_576x704_0.jpg +2 -2
- samples/unet_608x704_0.jpg +2 -2
- samples/unet_640x704_0.jpg +2 -2
- samples/unet_672x704_0.jpg +2 -2
- samples/unet_704x384_0.jpg +2 -2
- samples/unet_704x416_0.jpg +2 -2
- samples/unet_704x448_0.jpg +2 -2
- samples/unet_704x480_0.jpg +2 -2
- samples/unet_704x512_0.jpg +2 -2
- samples/unet_704x544_0.jpg +2 -2
- samples/unet_704x576_0.jpg +2 -2
- samples/unet_704x608_0.jpg +2 -2
- samples/unet_704x640_0.jpg +2 -2
- samples/unet_704x672_0.jpg +2 -2
- samples/unet_704x704_0.jpg +2 -2
- test.ipynb +2 -2
- unet/diffusion_pytorch_model.safetensors +1 -1
README.md
CHANGED
|
@@ -20,7 +20,7 @@ At AiArtLab, we strive to create a free, compact and fast model that can be trai
|
|
| 20 |
- Custom VAE: 32ch8x16x
|
| 21 |
- Speed: Sampling: 100%|██████████| 40/40 [00:01<00:00, 29.98it/s]
|
| 22 |
- Resolution: Default 1024x1408, trained from 768 to 1408 with step 64 (384/704/32)
|
| 23 |
-
- Limitations: trained on small datasets ~1-2kk, focused on art / illustrations / anime (with ~10% photo)
|
| 24 |
- Captions: danbooru, natural (short/medium), trained with 250 max toks
|
| 25 |
|
| 26 |
[Online demo on HF space](https://huggingface.co/spaces/LoveScapeAI/sdxs)
|
|
@@ -63,7 +63,7 @@ pipe = DiffusionPipeline.from_pretrained(
|
|
| 63 |
prompt = "1girl, smiling, red eyes, blue hair, white shirt"
|
| 64 |
refined = pipe.refine_prompts(prompt)[0]
|
| 65 |
|
| 66 |
-
negative_prompt="low quality"
|
| 67 |
|
| 68 |
image = pipe(
|
| 69 |
prompt=refined,
|
|
|
|
| 20 |
- Custom VAE: 32ch8x16x
|
| 21 |
- Speed: Sampling: 100%|██████████| 40/40 [00:01<00:00, 29.98it/s]
|
| 22 |
- Resolution: Default 1024x1408, trained from 768 to 1408 with step 64 (384/704/32)
|
| 23 |
+
- Limitations: trained on small datasets ~1-2kk, focused on art / illustrations / anime (with ~10% photo / use "photo" in negative prompt)
|
| 24 |
- Captions: danbooru, natural (short/medium), trained with 250 max toks
|
| 25 |
|
| 26 |
[Online demo on HF space](https://huggingface.co/spaces/LoveScapeAI/sdxs)
|
|
|
|
| 63 |
prompt = "1girl, smiling, red eyes, blue hair, white shirt"
|
| 64 |
refined = pipe.refine_prompts(prompt)[0]
|
| 65 |
|
| 66 |
+
negative_prompt="low quality, bad quality, photo, low details"
|
| 67 |
|
| 68 |
image = pipe(
|
| 69 |
prompt=refined,
|
media/boy.jpg
ADDED
|
Git LFS Details
|
media/girl.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
media/result_grid.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_384x704_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_416x704_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_448x704_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_480x704_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_512x704_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_544x704_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_576x704_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_608x704_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_640x704_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_672x704_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_704x384_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_704x416_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_704x448_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_704x480_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_704x512_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_704x544_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_704x576_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_704x608_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_704x640_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_704x672_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
samples/unet_704x704_0.jpg
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
test.ipynb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fadf36d8648709184149074a61476fde0652e55c36dc0c20014cbb4043dbb673
|
| 3 |
+
size 17570355
|
unet/diffusion_pytorch_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3210307232
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e70f41443a38e7af9b0115a30585cdf2a19a7449950b527d99ff71fa7160af5
|
| 3 |
size 3210307232
|