ell-hol commited on
Commit
d7ee783
·
verified ·
1 Parent(s): 3c710d9

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. README.md +46 -0
  2. config.yaml +78 -0
  3. lora.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - replicate
12
+ base_model: "black-forest-labs/FLUX.1-dev"
13
+ pipeline_tag: text-to-image
14
+ # widget:
15
+ # - text: >-
16
+ # prompt
17
+ # output:
18
+ # url: https://...
19
+ instance_prompt: WSTF
20
+ ---
21
+
22
+ # Fx Dv Lr Wf Ref Rdrs
23
+
24
+ <Gallery />
25
+
26
+ Trained on Replicate using:
27
+
28
+ https://replicate.com/ostris/flux-dev-lora-trainer/train
29
+
30
+
31
+ ## Trigger words
32
+ You should use `WSTF` to trigger the image generation.
33
+
34
+
35
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
36
+
37
+ ```py
38
+ from diffusers import AutoPipelineForText2Image
39
+ import torch
40
+
41
+ pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
42
+ pipeline.load_lora_weights('ell-hol/fx-dv-lr-wf-ref-rdrs', weight_name='lora.safetensors')
43
+ image = pipeline('your prompt').images[0]
44
+ ```
45
+
46
+ 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)
config.yaml ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ job: custom_job
2
+ config:
3
+ name: flux_train_replicate
4
+ process:
5
+ - type: custom_sd_trainer
6
+ training_folder: output
7
+ device: cuda:0
8
+ trigger_word: WSTF
9
+ network:
10
+ type: lora
11
+ linear: 24
12
+ linear_alpha: 24
13
+ save:
14
+ dtype: float16
15
+ save_every: 100
16
+ max_step_saves_to_keep: 1
17
+ datasets:
18
+ - folder_path: input_images
19
+ caption_ext: txt
20
+ caption_dropout_rate: 0.05
21
+ shuffle_tokens: false
22
+ cache_latents_to_disk: false
23
+ cache_latents: true
24
+ resolution:
25
+ - 512
26
+ - 768
27
+ - 1024
28
+ - 1440
29
+ train:
30
+ batch_size: 1
31
+ steps: 1500
32
+ gradient_accumulation_steps: 1
33
+ train_unet: true
34
+ train_text_encoder: false
35
+ content_or_style: balanced
36
+ gradient_checkpointing: true
37
+ noise_scheduler: flowmatch
38
+ optimizer: adamw8bit
39
+ lr: 0.0004
40
+ ema_config:
41
+ use_ema: true
42
+ ema_decay: 0.99
43
+ dtype: bf16
44
+ model:
45
+ name_or_path: FLUX.1-dev
46
+ is_flux: true
47
+ quantize: false
48
+ sample:
49
+ sampler: flowmatch
50
+ sample_every: 100
51
+ width: 1024
52
+ height: 1024
53
+ prompts:
54
+ - A bustling indoor scene at a mall, featuring vibrant shops with modern storefronts,
55
+ fashionable shoppers carrying branded bags, and sleek architectural details
56
+ like glass railings and polished floors. Bright lighting from skylights and
57
+ ceiling fixtures creates a lively and energetic atmosphere, capturing the
58
+ essence of a busy shopping day, WSTF style.
59
+ - An elegant cafe inside a mall, with modern seating arrangements, cozy lighting,
60
+ and patrons enjoying artisanal coffee and desserts. The background shows stylish
61
+ decor, a touch of greenery, and the buzz of mall activity, blending sophistication
62
+ with a casual vibe, WSTF style.
63
+ - A wide-angle shot of the central atrium in a Mall, showcasing its expansive
64
+ space with large decorative elements, a water fountain, and escalators leading
65
+ to various levels. People of all ages are walking, shopping, and relaxing,
66
+ immersed in the vibrant and luxurious mall experience, WSTF style.
67
+ - A winter-themed promotional event at a mall, featuring a beautifully decorated
68
+ area with fairy lights, a Christmas tree, and festive displays. Shoppers in
69
+ coats and scarves enjoy the cheerful atmosphere, and a Santa Claus figure
70
+ is interacting with children near a pop-up photo booth, WSTF style.
71
+ neg: ''
72
+ seed: 42
73
+ walk_seed: true
74
+ guidance_scale: 3.5
75
+ sample_steps: 28
76
+ meta:
77
+ name: flux_train_replicate
78
+ version: '1.0'
lora.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d0fb5478cbf0962c4eac098e45d215726a7a89eec14510c9c9c52ee5748c035
3
+ size 257887544