Type | |
Stats | 175 98 600 |
Reviews | (23) |
Published | Oct 18, 2024 |
Base Model | |
Training | Steps: 25,600 Epochs: 16 |
Usage Tips | Strength: 1 |
Trigger Words | _GTA_VC_ |
Hash | AutoV2 31324949BA |
Trained for 25,600 steps on 100 GTA: VC screenshots, mix of HUD and no-HUD, captioned by GPT-4o and hand-edited.
--cache_latents_to_disk ^
--save_model_as safetensors ^
--sdpa --persistent_data_loader_workers ^
--max_data_loader_n_workers 2 ^
--seed 42 ^
--gradient_checkpointing ^
--mixed_precision bf16 ^
--save_precision bf16 ^
--network_module networks.lora_flux ^
--network_dim 4 ^
--optimizer_type adamw8bit ^--sample_prompts="D:\Pinokio\api\fluxgym.git\outputs\gta-vice-city\sample_prompts.txt" --sample_every_n_steps="250" ^
--learning_rate 5e-4 ^
--cache_text_encoder_outputs ^
--cache_text_encoder_outputs_to_disk ^
--fp8_base ^
--highvram ^
--max_train_epochs 16 ^
--save_every_n_epochs 1 ^
--dataset_config "D:\Pinokio\api\fluxgym.git\outputs\gta-vice-city\dataset.toml" ^
--output_dir "D:\Pinokio\api\fluxgym.git\outputs\gta-vice-city" ^
--output_name gta-vice-city ^
--timestep_sampling shift ^
--discrete_flow_shift 3.1582 ^
--model_prediction_type raw ^
--guidance_scale 1 ^
--loss_type l2 ^
--bucket_reso_steps 64 ^
--cache_latents ^
--caption_dropout_every_n_epochs 2 ^
--dataset_repeats 2 ^
--enable_bucket ^
--full_bf16