aleksa-codes commited on
Commit
b4e1031
1 Parent(s): b5576ed

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +44 -17
README.md CHANGED
@@ -1,40 +1,67 @@
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
- language:
6
- - en
7
  tags:
 
8
  - flux
9
- - diffusers
10
  - lora
11
- base_model: "black-forest-labs/FLUX.1-dev"
12
  pipeline_tag: text-to-image
13
- instance_prompt: GHIBSKY
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  ---
15
 
16
- # Flux Ghibsky Illustration
17
 
18
- Flux LoRA, use `GHIBSKY style` at the start to trigger generation, creates serene and enchanting landscapes with vibrant, surreal skies and intricate, Ghibli-inspired elements reminiscent of the atmospheric beauty found in Makoto Shinkai's works.
19
 
20
- Trained on Replicate using:
21
 
22
- https://replicate.com/ostris/flux-dev-lora-trainer/train
23
 
 
24
 
25
  ## Trigger words
26
- You should use `GHIBSKY` to trigger the image generation.
27
 
 
 
 
 
 
28
 
29
  ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
30
 
31
  ```py
32
  from diffusers import AutoPipelineForText2Image
33
  import torch
34
-
35
- pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
36
  pipeline.load_lora_weights('aleksa-codes/flux-ghibsky-illustration', weight_name='lora.safetensors')
37
- image = pipeline('your prompt').images[0]
38
  ```
39
 
40
- For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
 
 
 
 
 
1
  ---
 
 
 
 
 
2
  tags:
3
+ - text-to-image
4
  - flux
 
5
  - lora
6
+ - diffusers
7
  pipeline_tag: text-to-image
8
+ thumbnail: "https://tjzk.replicate.delivery/models_models_cover_image/e5bc70de-c6ae-497f-bf2c-7e81b1183f05/out-0.jpg"
9
+ widget:
10
+ - text: GHIBSKY style, a cat on a windowsill gazing out at a starry night sky and distant city lights
11
+ output:
12
+ url: images/example1.jpg
13
+ - text: GHIBSKY style, a fisherman casting a line into a peaceful village lake surrounded by quaint cottages
14
+ output:
15
+ url: images/example2.jpg
16
+ - text: GHIBSKY style, cozy mountain cabin covered in snow, with smoke curling from the chimney and a warm, inviting light spilling through the windows
17
+ output:
18
+ url: images/example3.jpg
19
+ - text: GHIBSKY style, Mykonos
20
+ output:
21
+ url: images/example4.jpg
22
+ - text: GHIBSKY style, an orange Lamborghini driving down a hill road at night with a beautiful ocean view in the background, side view, no text
23
+ output:
24
+ url: images/example5.jpg
25
+ - text: GHIBSKY style, a small Yorkie on a windowsill during a snowy winter night, with a warm, cozy glow from inside and soft snowflakes drifting outside
26
+ output:
27
+ url: images/example6.jpg
28
+ base_model: black-forest-labs/FLUX.1-dev
29
+ instance_prompt: GHIBSKY style
30
+ license: other
31
+ license_name: flux-1-dev-non-commercial-license
32
+ license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
33
  ---
34
 
35
+ # Flux Ghibsky Illustration: Create Serene and Enchanting Landscapes
36
 
37
+ <Gallery />
38
 
39
+ ## Model description
40
 
41
+ The Flux Ghibsky Illustration model generates landscapes that combine serene, surreal skies with Ghibli-inspired details. It’s ideal for crafting dreamy scenes or capturing the essence of a Makoto Shinkai film. You can also run this model on Replicate. Feedback is welcome!
42
 
43
+ https://replicate.com/aleksa-codes/flux-ghibsky-illustration
44
 
45
  ## Trigger words
 
46
 
47
+ Use `GHIBSKY style` to invoke the model’s unique aesthetic. It’s best to start your prompt with the trigger word, followed by descriptions of your scene, such as nature, skies, houses, roads, villages, etc
48
+
49
+ ## Download model
50
+
51
+ [Download the *.safetensors LoRA](https://huggingface.co/aleksa-codes/flux-ghibsky-illustration/tree/main) in the Files & versions tab.
52
 
53
  ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
54
 
55
  ```py
56
  from diffusers import AutoPipelineForText2Image
57
  import torch
58
+ pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to('cuda')
 
59
  pipeline.load_lora_weights('aleksa-codes/flux-ghibsky-illustration', weight_name='lora.safetensors')
60
+ image = pipeline('GHIBSKY style, a serene lakeside village with colorful houses and towering mountains under a dreamy sky').images[0]
61
  ```
62
 
63
+ For more details, including weighting, merging, and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters).
64
+
65
+ ## License
66
+
67
+ Please adhere to the licensing terms as described [here](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).