Instructions to use crystantine/Avanza24 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use crystantine/Avanza24 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("crystantine/Avanza24") prompt = "AV4NZ4" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download config.yaml from crystantine/Avanza24: direct link, hf CLI and curl.
- Browser
- Download file 1.37 kB
-
https://huggingface.co/crystantine/Avanza24/resolve/main/config.yaml
- Command line
-
hf download hf://crystantine/Avanza24/config.yaml
-
curl -L -o config.yaml https://huggingface.co/crystantine/Avanza24/resolve/main/config.yaml
1.37 kB
| job: extension | |
| config: | |
| name: AVANZA24 | |
| process: | |
| - type: sd_trainer | |
| training_folder: output/your_model | |
| performance_log_every: 1000 | |
| device: cuda:0 | |
| trigger_word: AV4NZ4 | |
| network: | |
| type: lora | |
| linear: 16 | |
| linear_alpha: 16 | |
| save: | |
| dtype: float16 | |
| save_every: 250 | |
| max_step_saves_to_keep: 4 | |
| push_to_hub: true | |
| hf_repo_id: crystantine/Avanza24 | |
| hf_private: false | |
| datasets: | |
| - folder_path: AV4NZ4 | |
| caption_ext: txt | |
| caption_dropout_rate: 0.05 | |
| shuffle_tokens: true | |
| cache_latents_to_disk: true | |
| resolution: | |
| - 512 | |
| - 768 | |
| - 1024 | |
| train: | |
| batch_size: 1 | |
| steps: 2000 | |
| gradient_accumulation_steps: 1 | |
| train_unet: true | |
| train_text_encoder: false | |
| gradient_checkpointing: true | |
| noise_scheduler: flowmatch | |
| optimizer: adamw8bit | |
| lr: 0.0002 | |
| skip_first_sample: true | |
| ema_config: | |
| use_ema: true | |
| ema_decay: 0.99 | |
| dtype: bf16 | |
| model: | |
| name_or_path: black-forest-labs/FLUX.1-dev | |
| is_flux: true | |
| quantize: true | |
| sample: | |
| sampler: flowmatch | |
| sample_every: 250 | |
| width: 1024 | |
| height: 1024 | |
| prompts: '' | |
| neg: '' | |
| seed: 42 | |
| walk_seed: true | |
| guidance_scale: 4 | |
| sample_steps: 20 | |
| meta: | |
| name: '[your name]' | |
| version: '1.0' | |