first commit
Browse files- .gitattributes +4 -0
- README.md +74 -0
- images/input2.jpg +0 -0
- images/input2.png +0 -0
- images/input3.jpeg +3 -0
- images/input5.jpg +3 -0
- images/input7.jpg +0 -0
- images/output2.jpeg +0 -0
- images/output3.jpeg +0 -0
- images/output5.jpeg +3 -0
- images/output7.jpeg +3 -0
- metallic-objects-kontext-dev-lora.safetensors +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
images/input3.jpeg filter=lfs diff=lfs merge=lfs -text
|
37 |
+
images/input5.jpg filter=lfs diff=lfs merge=lfs -text
|
38 |
+
images/output5.jpeg filter=lfs diff=lfs merge=lfs -text
|
39 |
+
images/output7.jpeg filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- flux
|
4 |
+
- image-to-image
|
5 |
+
- lora
|
6 |
+
- fal
|
7 |
+
- diffusers
|
8 |
+
- ilkerizg
|
9 |
+
language: en
|
10 |
+
base_model: black-forest-labs/FLUX.1-Kontext-dev
|
11 |
+
instance_prompt: Make it metallic with a black background and a 3D perspective
|
12 |
+
license_name: flux1-dev-non-commercial-license
|
13 |
+
license_link: https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev/blob/main/LICENSE.md
|
14 |
+
license: other
|
15 |
+
widget:
|
16 |
+
- src: images/input2.jpg
|
17 |
+
prompt: Make it metallic with a black background and a 3D perspective
|
18 |
+
output:
|
19 |
+
url: images/output2.jpeg
|
20 |
+
- src: images/input3.png
|
21 |
+
prompt: Make it metallic with a black background and a 3D perspective
|
22 |
+
output:
|
23 |
+
url: images/output3.jpeg
|
24 |
+
- src: images/input5.jpg
|
25 |
+
prompt: Make it metallic with a black background and a 3D perspective
|
26 |
+
output:
|
27 |
+
url: images/output5.jpeg
|
28 |
+
- src: images/input7.jpg
|
29 |
+
prompt: Make it metallic with a black background and a 3D perspective
|
30 |
+
output:
|
31 |
+
url: images/output7.jpeg
|
32 |
+
---
|
33 |
+
|
34 |
+
# Metallic Objects Kontext Dev LoRA
|
35 |
+
|
36 |
+
<Gallery />
|
37 |
+
|
38 |
+
This is a LoRA (Low-Rank Adaptation) model that has been trained to transform input images into a metallic style, featuring a black background and a 3D perspective.
|
39 |
+
|
40 |
+
## Table of Contents
|
41 |
+
- [Model Details](#model-details)
|
42 |
+
- [Uses](#uses)
|
43 |
+
- [Training](#training)
|
44 |
+
|
45 |
+
## Model Details
|
46 |
+
|
47 |
+
**Model Description:** This model is a LoRA fine-tune of `black-forest-labs/FLUX.1-Kontext-dev`. It's designed to be used in an image-to-image pipeline to apply a specific artistic style. When prompted with "Make it metallic with a black background and a 3D perspective", it converts regular images into 3D-looking metallic objects on a dark background.
|
48 |
+
|
49 |
+
* **Developed by:** [ilkerizg](https://huggingface.co/ilkerizg)
|
50 |
+
* **Model Type:** LoRA for Image-to-Image generation
|
51 |
+
* **Language(s):** English
|
52 |
+
* **License:** [flux1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev/blob/main/LICENSE.md)
|
53 |
+
* **Parent Model:** [black-forest-labs/FLUX.1-Kontext-dev](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev)
|
54 |
+
* **Resources for more information:**
|
55 |
+
* [Download the weights](https://huggingface.co/ilkerizg/metallic-objects-kontext-dev-lora/resolve/main/metallic-objects-kontext-lora.safetensors)
|
56 |
+
* [Try the model directly on fal.ai](https://fal.ai/models/fal-ai/flux-kontext-lora?fromTraining=fe1a8832-be01-4df6-9b26-5dcbcde83d42)
|
57 |
+
|
58 |
+
## Uses
|
59 |
+
|
60 |
+
#### Direct Use
|
61 |
+
This model is intended to be used for artistic image generation. You can use it to apply a "metallic object" style to your own images. The model works best when using the trigger phrase: "**Make it metallic with a black background and a 3D perspective**".
|
62 |
+
|
63 |
+
## Training
|
64 |
+
|
65 |
+
#### Training Data
|
66 |
+
I trained the model on a custom dataset of 20 paired (before and after) images of various objects to learn the "metallic" style transformation.
|
67 |
+
|
68 |
+
#### Training Procedure
|
69 |
+
I performed the training using the [FLUX Kontext Trainer on fal.ai](https://fal.ai/models/fal-ai/flux-kontext-trainer/playground).
|
70 |
+
The base model for training was `black-forest-labs/FLUX.1-Kontext-dev`.
|
71 |
+
|
72 |
+
**Hyperparameters:**
|
73 |
+
* **Learning Rate:** 0.0001
|
74 |
+
* **Steps:** 1300
|
images/input2.jpg
ADDED
![]() |
images/input2.png
ADDED
![]() |
images/input3.jpeg
ADDED
![]() |
Git LFS Details
|
images/input5.jpg
ADDED
![]() |
Git LFS Details
|
images/input7.jpg
ADDED
![]() |
images/output2.jpeg
ADDED
![]() |
images/output3.jpeg
ADDED
![]() |
images/output5.jpeg
ADDED
![]() |
Git LFS Details
|
images/output7.jpeg
ADDED
![]() |
Git LFS Details
|
metallic-objects-kontext-dev-lora.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7ce7fd761580d4bf039306e24f3c0066044f859a2a604e8404de49e58df6b5d
|
3 |
+
size 306596088
|