Instructions to use glif-loradex-trainer/insectagon_Architect_render1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use glif-loradex-trainer/insectagon_Architect_render1 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("glif-loradex-trainer/insectagon_Architect_render1") prompt = "Batman [R3nderd]" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
| config: | |
| name: Architect_render1 | |
| process: | |
| - datasets: | |
| - cache_latents_to_disk: true | |
| caption_dropout_rate: 0.2 | |
| caption_ext: txt | |
| folder_path: /root/lorahub/Architect_render1/dataset | |
| resolution: | |
| - 1024 | |
| shuffle_tokens: true | |
| token_dropout_rate: 0.01 | |
| device: cuda:0 | |
| model: | |
| is_flux: true | |
| name_or_path: black-forest-labs/FLUX.1-dev | |
| quantize: true | |
| text_encoder_bits: 8 | |
| network: | |
| linear: 42 | |
| linear_alpha: 42 | |
| transformer_only: true | |
| type: lora | |
| performance_log_every: 500 | |
| sample: | |
| guidance_scale: 3.5 | |
| height: 1024 | |
| neg: '' | |
| prompts: | |
| - Batman [R3nderd] | |
| - 1967 Datsun 240z action scene [R3nderd] | |
| - closeup,side view, face of a sad rusty robot crying in the rain [R3nderd] | |
| - A dark dramatic scene,man and woman, maximal sorrow, new york city at night | |
| in the rain [R3nderd] | |
| - darkwing duck wearing black trenchcoat, abyss black void coat, shades of darkness, | |
| no light source, hand drawn, animated, rotoscope [R3nderd] | |
| - closeup of the face of a beautiful woman with tears in her eyes [R3nderd] | |
| sample_every: 500 | |
| sample_steps: 25 | |
| sampler: flowmatch | |
| seed: 777 | |
| walk_seed: true | |
| width: 1024 | |
| save: | |
| dtype: float16 | |
| max_step_saves_to_keep: 3 | |
| save_every: 500 | |
| save_format: diffusers | |
| train: | |
| batch_size: 1 | |
| dtype: bf16 | |
| ema_config: | |
| ema_decay: 0.99 | |
| use_ema: true | |
| gradient_accumulation_steps: 1 | |
| gradient_checkpointing: true | |
| linear_timesteps: true | |
| loss_type: mse | |
| lr: 0.5 | |
| noise_scheduler: flowmatch | |
| optimizer: prodigy | |
| reg_weight: 0.5 | |
| steps: 3000 | |
| target_noise_multiplier: 1.0 | |
| train_text_encoder: false | |
| train_unet: true | |
| training_folder: /root/lorahub | |
| trigger_word: R3nderd | |
| type: sd_trainer | |
| job: extension | |
| meta: | |
| description: architecture rendering style | |