physical violence

revealing clothes

weapon violence

pg-13

corpses

wide hips

convenient censoring

oral invitation

thick thighs

huge breasts

downblouse

suggestive

sexy

pg13

sexual situations

disturbing

male nudity

female swimwear or underwear

male swimwear or underwear

partial nudity

graphic violence or gore

emaciated bodies

exposed female nipple

female nudity

undressed

male underwear

female swimwear

female underwear

breasts out

strapless leotard

breast out

one breast out

gigantic breasts

huge butt

covered nipples

hair over breasts

no panties

sitting on face

nude

lingerie

nsfw

adult toys

nudity

graphic male nudity

illustrated explicit nudity

graphic female nudity

sexual intent

genitals

porn

futanari

hentai

peeing

blowjob

sexual activity

vore

anal

dildo riding

oral

incest

hanging

hate symbols

nazi party

white supremacy

self injury

extremist

hate speech

diapers

urine

scat

child on child

bukkake

fellatio

bikini

cumshot

implied fellatio

eat_cum

cumdrip

cum in pussy

cum on face

after fellatio

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

To get the spinning effect, write something like this in prompt:<pre><code>The [object] froze for a few seconds, and then abruptly began to spin in place.</code></pre>You can find detailed information about the versions in these articles:<ul><li><a target="_blank" rel="ugc" href="https://civitai.com/articles/20210">[Wan 2.2 T2V-A14B]</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/articles/20996">[Wan 2.2 TI2V-5B]</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/articles/21831">[Wan 2.2 I2V-A14B]</a></li><li><a rel="ugc" href="https://civitai.com/articles/25494">[LTX-2]</a></li></ul>

LTX-2-dev

dataset.toml<pre><code>resolutions = [[368, 368]]
enable_ar_bucket = true
min_ar = 0.5
max_ar = 2.0
num_ar_buckets = 7
frame_buckets = [ 1, 48, 51, 72, 75, 80, 81,]
[[directory]]
path = "/home/user/oiia_cat_videos_16fps"
num_repeats = 4</code></pre>train.toml<pre><code>output_dir = "/home/user/oiia_cat_A14B_i2v_v2/A14B"
dataset = "/home/user/dataset_A14B.toml"
epochs = 120
micro_batch_size_per_gpu = 1
pipeline_stages = 1
gradient_accumulation_steps = 1
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 = 6
activation_checkpointing = true
partition_method = "parameters"
save_dtype = "bfloat16"
caching_batch_size = 1
steps_per_print = 10
video_clip_mode = "single_beginning"
blocks_to_swap = 32

[model]
type = "wan"
ckpt_path = "/home/user/Wan2.2-I2V-A14B"
dtype = "bfloat16"
transformer_dtype = "float8"
timestep_sample_method = "logit_normal"
transformer_path = "/home/user/Wan2.2-I2V-A14B/high_noise_model"
min_t = 0.875
max_t = 1

[adapter]
type = "lora"
rank = 32
dtype = "bfloat16"

[optimizer]
type = "adamw_optimi"
lr = 1e-4
betas = [ 0.9, 0.99,]
weight_decay = 0.01
eps = 1e-8</code></pre>

wan2.2-i2v-A14B-HIGH

dataset.toml<pre><code>resolutions = [[368, 368]]
enable_ar_bucket = true
min_ar = 0.5
max_ar = 2.0
num_ar_buckets = 7
frame_buckets = [ 1, 48, 51, 72, 75, 80, 81,]
[[directory]]
path = "/home/user/oiia_cat_videos_16fps"
num_repeats = 4</code></pre>train.toml<pre><code>output_dir = "/home/user/oiia_cat_A14B_i2v_v2/A14B"
dataset = "/home/user/dataset_A14B.toml"
epochs = 120
micro_batch_size_per_gpu = 1
pipeline_stages = 1
gradient_accumulation_steps = 1
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 = 6
activation_checkpointing = true
partition_method = "parameters"
save_dtype = "bfloat16"
caching_batch_size = 1
steps_per_print = 10
video_clip_mode = "single_beginning"
blocks_to_swap = 32

[model]
type = "wan"
ckpt_path = "/home/user/Wan2.2-I2V-A14B"
dtype = "bfloat16"
transformer_dtype = "float8"
timestep_sample_method = "logit_normal"
transformer_path = "/home/user/Wan2.2-I2V-A14B/low_noise_model"
min_t = 0
max_t = 0.875

[adapter]
type = "lora"
rank = 32
dtype = "bfloat16"

[optimizer]
type = "adamw_optimi"
lr = 1e-4
betas = [ 0.9, 0.99,]
weight_decay = 0.01
eps = 1e-8</code></pre>

wan2.2-i2v-A14B-LOW

dataset.toml<pre><code>resolutions = [ [ 1280, 704], [704, 1280]]
enable_ar_bucket = true
min_ar = 0.5
max_ar = 2.0
num_ar_buckets = 7
ar_buckets = [[1280, 704], [704, 1280]]
frame_buckets = [ 1, 48, 51, 72, 75, 81,]
[[directory]]
path = "/home/user/oiia_cat_videos_24fps"
num_repeats = 30</code></pre>train.toml<pre><code>output_dir = "/home/user/training_results/oiia_cat_videos_24fps/5B"
dataset = "/home/user/dataset_5B.toml"
epochs = 20
micro_batch_size_per_gpu = 1
pipeline_stages = 1
gradient_accumulation_steps = 1
gradient_clipping = 1
warmup_steps = 100
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 = 1
activation_checkpointing = true
partition_method = "parameters"
save_dtype = "bfloat16"
caching_batch_size = 1
steps_per_print = 10
video_clip_mode = "single_beginning"
blocks_to_swap = 28

[model]
type = "wan"
ckpt_path = "/home/user/huggingface_wan/Wan2.2-TI2V-5B"
dtype = "bfloat16"
transformer_dtype = "float8"
timestep_sample_method = "logit_normal"

[adapter]
type = "lora"
rank = 64
dtype = "bfloat16"

[optimizer]
type = "adamw_optimi"
lr = 8e-5
betas = [ 0.9, 0.99,]
weight_decay = 0.01
eps = 1e-8</code></pre>

wan2.2-ti2v-5B

dataset<pre><code>resolutions = [ [ 192, 342,], [ 480, 854,],]
enable_ar_bucket = true
min_ar = 0.5
max_ar = 2.0
num_ar_buckets = 7
frame_buckets = [ 1, 48, 51, 72, 75, 80, 81,]
[[directory]]
path = "/home/user/oiia_cat_videos_16fps"
num_repeats = 4</code></pre>train.toml<pre><code>output_dir = "/home/user/oiia_cat_A14B/A14B"
dataset = "/home/user/dataset_A14B.toml"
epochs = 200
micro_batch_size_per_gpu = 1
pipeline_stages = 1
gradient_accumulation_steps = 1
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
activation_checkpointing = true
partition_method = "parameters"
save_dtype = "bfloat16"
caching_batch_size = 1
steps_per_print = 10
video_clip_mode = "single_beginning"
blocks_to_swap = 32

[model]
type = "wan"
ckpt_path = "/home/user/Wan2.2-T2V-A14B"
dtype = "bfloat16"
transformer_dtype = "float8"
timestep_sample_method = "logit_normal"
transformer_path = "/home/user/Wan2.2-T2V-A14B/high_noise_model"
min_t = 0.875
max_t = 1

[adapter]
type = "lora"
rank = 32
dtype = "bfloat16"

[optimizer]
type = "adamw_optimi"
lr = 5e-5
betas = [ 0.9, 0.99,]
weight_decay = 0.01
eps = 1e-8</code></pre>

wan2.2-t2v-A14B-HIGH

dataset.toml<pre><code>resolutions = [ [ 192, 342,], [ 480, 854,],]
enable_ar_bucket = true
min_ar = 0.5
max_ar = 2.0
num_ar_buckets = 7
frame_buckets = [ 1, 48, 51, 72, 75, 80, 81,]
[[directory]]
path = "/home/user/oiia_cat_videos_16fps"
num_repeats = 4</code></pre>train.toml<pre><code>output_dir = "/home/user/oiia_cat_A14B/A14B"
dataset = "/home/user/dataset_A14B.toml"
epochs = 200
micro_batch_size_per_gpu = 1
pipeline_stages = 1
gradient_accumulation_steps = 1
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
activation_checkpointing = true
partition_method = "parameters"
save_dtype = "bfloat16"
caching_batch_size = 1
steps_per_print = 10
video_clip_mode = "single_beginning"
blocks_to_swap = 32

[model]
type = "wan"
ckpt_path = "/home/user/Wan2.2-T2V-A14B"
dtype = "bfloat16"
transformer_dtype = "float8"
timestep_sample_method = "logit_normal"
transformer_path = "/home/user/Wan2.2-T2V-A14B/low_noise_model"
min_t = 0
max_t = 0.875

[adapter]
type = "lora"
rank = 32
dtype = "bfloat16"

[optimizer]
type = "adamw_optimi"
lr = 5e-5
betas = [ 0.9, 0.99,]
weight_decay = 0.01
eps = 1e-8</code></pre>

wan2.2-t2v-A14B-LOW

OIIA (Spinning Cat)

vlcsnap-2025-05-18-20h54m31s079.png

Type	LoRA
Stats	80 0
Reviews	Positive (18)
Published	Jan 29, 2026
Base Model	LTXV2
Training	Steps: 2,500
Trigger Words	OIIA_cat
Hash	AutoV2 AFA17548E5