Upload 2 files
Browse files- FLUX-dev-lora-AntiBlur.safetensors +3 -0
- README (14).md +60 -0
FLUX-dev-lora-AntiBlur.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:328f945688a91b13b5603550cb615ccb218f1400b3456bf409e41d5dbf065655
|
| 3 |
+
size 687476088
|
README (14).md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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.
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
pipeline_tag: text-to-image
|
| 8 |
+
tags:
|
| 9 |
+
- lora
|
| 10 |
+
- Stable Diffusion
|
| 11 |
+
- image-generation
|
| 12 |
+
- Flux
|
| 13 |
+
- diffusers
|
| 14 |
+
base_model: black-forest-labs/FLUX.1-dev
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
[<img src="https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/light/join-our-discord-rev1.png?raw=true">](https://discord.gg/FHY2guThfy)
|
| 18 |
+
|
| 19 |
+
This repository provides a checkpoint with trained LoRA photorealism for
|
| 20 |
+
[FLUX.1-dev model](https://huggingface.co/black-forest-labs/FLUX.1-dev) by Black Forest Labs
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
# ComfyUI
|
| 24 |
+
|
| 25 |
+
[See our github](https://github.com/XLabs-AI/x-flux-comfyui) for comfy ui workflows.
|
| 26 |
+
|
| 27 |
+
# Training details
|
| 28 |
+
[XLabs AI](https://github.com/XLabs-AI) team is happy to publish fine-tuning Flux scripts, including:
|
| 29 |
+
|
| 30 |
+
- **LoRA** 🔥
|
| 31 |
+
- **ControlNet** 🔥
|
| 32 |
+
|
| 33 |
+
[See our github](https://github.com/XLabs-AI/x-flux) for train script and train configs.
|
| 34 |
+
|
| 35 |
+
# Training Dataset
|
| 36 |
+
Dataset has the following format for the training process:
|
| 37 |
+
|
| 38 |
+
```
|
| 39 |
+
├── images/
|
| 40 |
+
│ ├── 1.png
|
| 41 |
+
│ ├── 1.json
|
| 42 |
+
│ ├── 2.png
|
| 43 |
+
│ ├── 2.json
|
| 44 |
+
│ ├── ...
|
| 45 |
+
```
|
| 46 |
+
A .json file contains "caption" field with a text prompt.
|
| 47 |
+
|
| 48 |
+
# Inference
|
| 49 |
+
```bash
|
| 50 |
+
python3 demo_lora_inference.py \
|
| 51 |
+
--checkpoint lora.safetensors \
|
| 52 |
+
--prompt " handsome girl in a suit covered with bold tattoos and holding a pistol. Animatrix illustration style, fantasy style, natural photo cinematic"
|
| 53 |
+
```
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
# License
|
| 59 |
+
|
| 60 |
+
lora.safetensors falls under the [FLUX.1 [dev]](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md) Non-Commercial License<br/>
|