Upload folder using huggingface_hub
Browse files- README.md +35 -0
- config.json +45 -0
- decoder.pth +3 -0
- diffusion_pytorch_model.bin +3 -0
- diffusion_pytorch_model.safetensors +3 -0
- encoder.pth +3 -0
README.md
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# 🍰 Tiny AutoEncoder for FLUX.1
|
| 6 |
+
|
| 7 |
+
[TAEF1](https://github.com/madebyollin/taesd) is very tiny autoencoder which uses the same "latent API" as FLUX.1's VAE.
|
| 8 |
+
FLUX.1 is useful for real-time previewing of the FLUX.1 generation process.
|
| 9 |
+
|
| 10 |
+
This repo contains `.safetensors` versions of the TAEF1 weights.
|
| 11 |
+
|
| 12 |
+
## Using in 🧨 diffusers
|
| 13 |
+
|
| 14 |
+
```python
|
| 15 |
+
import torch
|
| 16 |
+
from diffusers import FluxPipeline, AutoencoderTiny
|
| 17 |
+
|
| 18 |
+
pipe = FluxPipeline.from_pretrained(
|
| 19 |
+
"black-forest-labs/FLUX.1-schnell", torch_dtype=torch.bfloat16
|
| 20 |
+
)
|
| 21 |
+
pipe.vae = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=torch.bfloat16)
|
| 22 |
+
pipe.enable_sequential_cpu_offload()
|
| 23 |
+
|
| 24 |
+
prompt = "slice of delicious New York-style berry cheesecake"
|
| 25 |
+
image = pipe(
|
| 26 |
+
prompt,
|
| 27 |
+
guidance_scale=0.0,
|
| 28 |
+
num_inference_steps=4,
|
| 29 |
+
max_sequence_length=256,
|
| 30 |
+
).images[0]
|
| 31 |
+
image.save("cheesecake.png")
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+

|
config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderTiny",
|
| 3 |
+
"_diffusers_version": "0.30.0",
|
| 4 |
+
"act_fn": "relu",
|
| 5 |
+
"block_out_channels": [
|
| 6 |
+
64,
|
| 7 |
+
64,
|
| 8 |
+
64,
|
| 9 |
+
64
|
| 10 |
+
],
|
| 11 |
+
"decoder_block_out_channels": [
|
| 12 |
+
64,
|
| 13 |
+
64,
|
| 14 |
+
64,
|
| 15 |
+
64
|
| 16 |
+
],
|
| 17 |
+
"encoder_block_out_channels": [
|
| 18 |
+
64,
|
| 19 |
+
64,
|
| 20 |
+
64,
|
| 21 |
+
64
|
| 22 |
+
],
|
| 23 |
+
"force_upcast": false,
|
| 24 |
+
"in_channels": 3,
|
| 25 |
+
"latent_channels": 16,
|
| 26 |
+
"latent_magnitude": 3,
|
| 27 |
+
"latent_shift": 0.5,
|
| 28 |
+
"num_decoder_blocks": [
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
1
|
| 33 |
+
],
|
| 34 |
+
"num_encoder_blocks": [
|
| 35 |
+
1,
|
| 36 |
+
3,
|
| 37 |
+
3,
|
| 38 |
+
3
|
| 39 |
+
],
|
| 40 |
+
"out_channels": 3,
|
| 41 |
+
"scaling_factor": 1.0,
|
| 42 |
+
"shift_factor": 0.0,
|
| 43 |
+
"upsample_fn": "nearest",
|
| 44 |
+
"upsampling_scaling_factor": 2
|
| 45 |
+
}
|
decoder.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:266d694daacad7794a404b3597e5d7bc4390385e90c73d74a8cacac7715b9969
|
| 3 |
+
size 2494680
|
diffusion_pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96cfac57ad0d2314b0bd78065b97266063196ee65cfc082a85be4abb9c89915c
|
| 3 |
+
size 9879238
|
diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:927f7de7f11bbd3b2d5ce402e608d97a7649e0921a9601995b044e8efc81e449
|
| 3 |
+
size 9848636
|
encoder.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a808e5093dd298a7df09329da3b81ba9bed968c97f289f32288023f93f2b53c
|
| 3 |
+
size 2494552
|