Download
1 variant available
The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.
IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
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