Upload README (20).md
Browse files- README (20).md +61 -10
README (20).md
CHANGED
|
@@ -1,13 +1,64 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: flux-1-dev-non-commercial-license
|
| 4 |
+
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
|
| 5 |
+
base_model:
|
| 6 |
+
- ashen0209/Flux-Dev2Pro
|
| 7 |
+
- black-forest-labs/FLUX.1-schnell
|
| 8 |
+
tags:
|
| 9 |
+
- text-to-image
|
| 10 |
+
- flux
|
| 11 |
+
- merge
|
| 12 |
+
widget:
|
| 13 |
+
- text: Example 1
|
| 14 |
+
output:
|
| 15 |
+
url: images/0015.webp
|
| 16 |
+
- text: Example 2
|
| 17 |
+
output:
|
| 18 |
+
url: images/0022.webp
|
| 19 |
+
- text: Example 3
|
| 20 |
+
output:
|
| 21 |
+
url: images/0012.webp
|
| 22 |
+
- text: Example 4
|
| 23 |
+
output:
|
| 24 |
+
url: images/0014.webp
|
| 25 |
+
- text: Example 5
|
| 26 |
+
output:
|
| 27 |
+
url: images/0033.webp
|
| 28 |
+
- text: Example 6
|
| 29 |
+
output:
|
| 30 |
+
url: images/0032.webp
|
| 31 |
---
|
| 32 |
|
| 33 |
+
# Flux D+S F8 Diffusers
|
| 34 |
+
|
| 35 |
+
A + B merge, meant for gradio inference, possibly build adapters on top with [diffusers](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_lora_flux.py).
|
| 36 |
+
|
| 37 |
+
<Gallery />
|
| 38 |
+
|
| 39 |
+
## Inference
|
| 40 |
+
|
| 41 |
+
[Instruction](https://huggingface.co/twodgirl/flux-dev-fp8-e4m3fn-diffusers)
|
| 42 |
+
|
| 43 |
+
This model needs 10 steps, otherwise the images remain blurry.
|
| 44 |
+
|
| 45 |
+
## ComfyUI
|
| 46 |
+
|
| 47 |
+
I convert all my checkpoints locally. There are 5+ file formats out there, they take up too much space.
|
| 48 |
+
|
| 49 |
+
Download the contents of this repo, then enter the directory. A script will convert the diffusers format to something that is compatible with ComfyUI.
|
| 50 |
+
|
| 51 |
+
```
|
| 52 |
+
cd flux-devpro-schnell-merge-fp8-e4m3fn-diffusers
|
| 53 |
+
pip install safetensors torch
|
| 54 |
+
python flux_devpro_ckpt.py transformer/diffusion_pytorch_model.safetensors flux-devpro-schnell.safetensors
|
| 55 |
+
mv flux-devpro-schnell.safetensors path/to/your/ComfyUI/models/unet/flux-devpro-schnell.safetensors
|
| 56 |
+
```
|
| 57 |
+
|
| 58 |
+
In the workflow, the LoadDiffusionModel node should take two values: flux-devpro-schnell.safetensors, fp8_e4m3fn.
|
| 59 |
+
|
| 60 |
+
Use of this code requires citation and attribution to the author via a link to their Hugging Face profile in all resulting work.
|
| 61 |
+
|
| 62 |
+
## Disclaimer
|
| 63 |
+
|
| 64 |
+
Sharing, reusing the model weights requires a link back to authors and their Hugging Face profile. The source models were uploaded by Ashen0209 and BFL.
|