Duplicate from ostris/vae-kl-f8-d16

Co-authored-by: Jaret Burkett <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,31 @@
+---
+license: mit
+library_name: diffusers
+---
+
+# Ostris VAE - KL-f8-d16
+
+A 16 channel VAE with 8x downsample. Trained from scratch on a balance of photos, artistic, text, cartoons, vector images. 
+
+It is lighter weight that most VAEs with only 57,266,643 parameters (vs SD3 VAE: 83,819,683) which means it is faster and uses less VRAM yet scores quite similarly
+on real images. Plus it is MIT licensed so you can do whatever you want with it.
+
+| VAE|PSNR (higher better)| LPIPS (lower better) | # params |
+|----|----|----|----|
+| sd-vae-ft-mse|26.939|0.0581|83,653,863|
+| SDXL|27.370|0.0540|83,653,863|
+| SD3|31.681|0.0187|83,819,683|
+| **Ostris KL-f8-d16** |**31.166**|**0.0198**|**57,266,643**|
+
+### Compare
+Check out the comparison at [imgsli](https://imgsli.com/Mjc2MjA3).
+
+
+### What do I do with this?
+
+If you don't know, you probably don't need this. This is made as an open source lighter version of a 16ch vae. 
+You would need to train it into a network before it is useful. I plan to do this myself for SD 1.5, SDXL, and possibly pixart. 
+[Follow me on Twitter](https://x.com/ostrisai) to keep up with my work on that. 
+
+### Note: Not SD3 compatable
+This VAE is not SD3 compatable as it is trained from scratch and has an entirely different latent space.

config.json

@@ -0,0 +1,36 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.29.0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    128,
+    256,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 16,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.24447420268654824,
+  "shift_factor": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2251290efaac0e7b2b6eb8871691dda37b7f0c3ee0fd11ba6ec29e82954092e2
+size 114560782