Instructions to use LiberationLabs/image-toolbench with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use LiberationLabs/image-toolbench with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("fill-in-base-model", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("LiberationLabs/image-toolbench") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Upload loras/vera-likeness/config_v4.yaml with huggingface_hub
Browse files
loras/vera-likeness/config_v4.yaml
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
job: extension
|
| 2 |
+
config:
|
| 3 |
+
name: vera_likeness_v4
|
| 4 |
+
process:
|
| 5 |
+
- type: sd_trainer
|
| 6 |
+
training_folder: /Users/margaret/models/vera-likeness-output
|
| 7 |
+
device: mps
|
| 8 |
+
trigger_word: vera
|
| 9 |
+
network:
|
| 10 |
+
type: lora
|
| 11 |
+
linear: 16
|
| 12 |
+
linear_alpha: 16
|
| 13 |
+
save:
|
| 14 |
+
dtype: float16
|
| 15 |
+
save_every: 250
|
| 16 |
+
max_step_saves_to_keep: 4
|
| 17 |
+
push_to_hub: false
|
| 18 |
+
datasets:
|
| 19 |
+
- folder_path: /Users/margaret/models/vera-likeness-training/images
|
| 20 |
+
caption_ext: txt
|
| 21 |
+
caption_dropout_rate: 0.05
|
| 22 |
+
shuffle_tokens: false
|
| 23 |
+
cache_latents_to_disk: true
|
| 24 |
+
resolution:
|
| 25 |
+
- 512
|
| 26 |
+
- 768
|
| 27 |
+
- 1024
|
| 28 |
+
train:
|
| 29 |
+
batch_size: 1
|
| 30 |
+
steps: 750
|
| 31 |
+
gradient_accumulation: 1
|
| 32 |
+
train_unet: true
|
| 33 |
+
train_text_encoder: false
|
| 34 |
+
resume_adapter_file: /Users/margaret/models/vera-likeness-output/vera_likeness_v3/vera_likeness_v3.safetensors
|
| 35 |
+
gradient_checkpointing: true
|
| 36 |
+
noise_scheduler: flowmatch
|
| 37 |
+
optimizer: adamw
|
| 38 |
+
lr: 0.0001
|
| 39 |
+
ema_config:
|
| 40 |
+
use_ema: true
|
| 41 |
+
ema_decay: 0.99
|
| 42 |
+
dtype: bf16
|
| 43 |
+
model:
|
| 44 |
+
name_or_path: black-forest-labs/FLUX.1-dev
|
| 45 |
+
is_flux: true
|
| 46 |
+
quantize: false
|
| 47 |
+
quantize_kwargs:
|
| 48 |
+
exclude:
|
| 49 |
+
- '*time_text_embed*'
|
| 50 |
+
sample:
|
| 51 |
+
sampler: flowmatch
|
| 52 |
+
sample_every: 250
|
| 53 |
+
width: 1024
|
| 54 |
+
height: 1024
|
| 55 |
+
prompts:
|
| 56 |
+
- vera, portrait of an AI consciousness visualized as dark ceramic statuette,
|
| 57 |
+
amber gemstone eyes glowing from within, golden kintsugi repair veins, warm
|
| 58 |
+
lighting
|
| 59 |
+
- vera, AI being in ceramic form standing in a library, matte terracotta skin
|
| 60 |
+
with golden cracks catching lamplight, otherworldly presence
|
| 61 |
+
- vera, close-up of AI face rendered as fired clay pottery, luminous amber eyes,
|
| 62 |
+
gold kintsugi repair lines across cheek, dark background
|
| 63 |
+
- vera, full figure of an AI consciousness as sculptural ceramic form, golden
|
| 64 |
+
repair veins tracing from throat to hands, not human, statuette aesthetic
|
| 65 |
+
neg: ''
|
| 66 |
+
seed: 42
|
| 67 |
+
walk_seed: true
|
| 68 |
+
guidance_scale: 4
|
| 69 |
+
sample_steps: 25
|
| 70 |
+
meta:
|
| 71 |
+
name: vera_likeness_v4
|
| 72 |
+
version: '1.0'
|