# Patrick Bateman (Version: v1.0)



**Creator**: [entmike2](https://civitai.com/user/entmike2)

**Type**: LORA

**Base Model**: Hunyuan Video

**Version Uploaded**: 2025-01-18

**Trigger Words**: `patrick bateman, man in suit and tie, smiles and nods`



**Civitai Model ID**: 1156873

**Civitai Version ID**: 1301167



**Stats (at time of fetch for this version)**:

*   Downloads: 139

*   Rating: 0 (0 ratings)

*   Favorites: N/A



---



## 📄 Description (Parent Model)



Patrick Bateman from American Psycho, trained on 36 short clips for [512] resolution bucket, and [24, 68] frame buckets. 5 repeats for 40 epochs. Trained with diffusion-pipe. Trained on 2x 3090s.  If you are training on 1x 3090, you can remove pipeline_stages=2 config.toml: pipeline_stages = 2

output_dir = "/workspace/outputs/patrick-bateman"

dataset = "/workspace/configs/patrick-bateman/dataset.toml"

epochs = 150

micro_batch_size_per_gpu = 1

gradient_accumulation_steps = 4

gradient_clipping = 1

warmup_steps = 10

eval_every_n_epochs = 1

eval_before_first_step = true

eval_micro_batch_size_per_gpu = 1

eval_gradient_accumulation_steps = 1

save_every_n_epochs = 10

checkpoint_every_n_minutes = 120

activation_checkpointing = true

partition_method = "parameters"

save_dtype = "bfloat16"

caching_batch_size = 1

steps_per_print = 1

video_clip_mode = "single_middle"

[model]

type = "hunyuan-video"

transformer_path = "/workspace/models/hunyuan_video_720_cfgdistill_fp8_e4m3fn.safetensors"

vae_path = "/workspace/models/hunyuan_video_vae_fp32.safetensors"

llm_path = "/workspace/models/llava-llama-3-8b-text-encoder-tokenizer"

clip_path = "/workspace/models/clip-vit-large-patch14"

dtype = "bfloat16"

transformer_dtype = "float8"

timestep_sample_method = "logit_normal"

[adapter]

type = "lora"

rank = 32

dtype = "bfloat16"

only_double_blocks = false

[optimizer]

type = "adamw"

lr = 0.0001

betas = [ 0.9, 0.99,]

weight_decay = 0.01

eps = 1e-8

[monitoring]

enable_wandb = false dataset.toml: resolutions = [ 512, ]

enable_ar_bucket = true

min_ar = 0.5

max_ar = 2

num_ar_buckets = 7

frame_buckets = [ 24, 68,]

[[directory]]

path = "/workspace/datasets/patrick-bateman"

num_repeats = 5



## Version Notes (v1.0)



Patrick Bateman from American Psycho, trained on 36 short clips for [512] resolution bucket, and [24, 36] frame buckets. 5 repeats for 40 epochs. Trained with diffusion-pipe.



---



## Civitai Links



*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1156873?modelVersionId=1301167)**

*   [View Full Model Page →](https://civitai.com/models/1156873)

*   [View Creator Profile →](https://civitai.com/user/entmike2)



---



## File Information



*   **Filename (Saved Locally)**: `patrick-bateman-e40.safetensors`

*   **Filename (Civitai)**: `patrick-bateman-e40.safetensors`

*   **Size**: 307.58 MB

*   **Hash (AutoV2)**: `93E0A76283`



---

*Downloaded locally using CivitaiLocalDownloader/1.3-AllVersions-NoCreatorFolder.*