You can find detailed information about the versions in these articles:<ul><li><a target="_blank" rel="ugc" href="https://civitai.com/articles/18990">[Wan 2.1 T2V-14B]</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/articles/18999">[Wan 2.2 TI2V-5B]</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/articles/23124">[Wan 2.2 T2V-A14B]</a></li><li><a rel="ugc" href="https://civitai.com/articles/30259">[LTX-2.3]</a></li></ul>

LTX-2.3

Training Detailsdataset.toml<pre><code>resolutions = [[192, 341] ,[480, 853], [600, 1067]]
enable_ar_bucket = true
min_ar = 0.5
max_ar = 2.0
num_ar_buckets = 7
frame_buckets = [ 1, 16, 33]
[[directory]]
path = "/home/user/beauty_of_rain_dataset/videos"
num_repeats = 1</code></pre>train.toml<pre><code>output_dir = "/home/user/beauty_of_rain/14B"
dataset = "/home/user/beauty_of_rain_dataset_14B.toml"
epochs = 60
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 = 3
activation_checkpointing = 'unsloth'
partition_method = "parameters"
save_dtype = "bfloat16"
caching_batch_size = 1
steps_per_print = 10
video_clip_mode = "multiple_overlapping"
blocks_to_swap = 32

[model]
type = "wan"
ckpt_path = "/home/user/Wan2.1-T2V-14B"
dtype = "bfloat16"
transformer_dtype = "float8"
timestep_sample_method = "logit_normal"

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

[optimizer]
type = 'AdamW8bitKahan'
lr = 5e-5
betas = [0.9, 0.99]
weight_decay = 0.01
stabilize = false</code></pre>

wan 2.1 t2v-14B

dataset.toml<pre><code>resolutions = [ [ 342, 192,], [ 854, 480,], [1067, 600]]
enable_ar_bucket = true
min_ar = 0.5
max_ar = 2.0
num_ar_buckets = 7
frame_buckets = [ 1, 16, 30, 33]
[[directory]]
path = "/home/beauty_of_rain_dataset/videos"
num_repeats = 2</code></pre>train.toml<pre><code>output_dir = "/home/beauty_of_rain_dataset/A14B"
dataset = "/home/dataset_v000_854_480_A14B.toml"
epochs = 100
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/Wan2.2-T2V-A14B"
dtype = "bfloat16"
transformer_dtype = "float8"
timestep_sample_method = "logit_normal"
transformer_path = "/home/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 = 7e-5
betas = [ 0.9, 0.99,]
weight_decay = 0.01
eps = 1e-8</code></pre>

wan 2.2 t2v-A14B HIGH

dataset.toml<pre><code>resolutions = [ [ 342, 192,], [ 854, 480,], [1067, 600]]
enable_ar_bucket = true
min_ar = 0.5
max_ar = 2.0
num_ar_buckets = 7
frame_buckets = [ 1, 16, 30, 33]
[[directory]]
path = "/home/beauty_of_rain_dataset/videos"
num_repeats = 2</code></pre>train.toml<pre><code>output_dir = "/home/beauty_of_rain_dataset/A14B"
dataset = "/home/dataset_v000_854_480_A14B.toml"
epochs = 100
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/Wan2.2-T2V-A14B"
dtype = "bfloat16"
transformer_dtype = "float8"
timestep_sample_method = "logit_normal"
transformer_path = "/home/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>

wan 2.2 t2v-A14B LOW

Training Detailsdataset.toml<pre><code>resolutions = [[ 1280, 704]]
enable_ar_bucket = true
min_ar = 0.5
max_ar = 2.0
num_ar_buckets = 7
ar_buckets = [[1280, 704]]
frame_buckets = [ 1, 24, 46, 81,]
[[directory]]
path = "/home/user/beauty_of_rain_dataset/videos"
num_repeats = 4</code></pre>train.toml<pre><code>output_dir = "/home/user/beauty_of_rain_dataset/5B"
dataset = "/home/user/beauty_of_rain_5B.toml"
epochs = 120
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 = 12
activation_checkpointing = true
partition_method = "parameters"
save_dtype = "bfloat16"
caching_batch_size = 1
steps_per_print = 10
video_clip_mode = "single_beginning"

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

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

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

wan 2.2 ti2v-5B

Beauty of rain

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

physical violence

weapon violence

wide hips

revealing clothes

downblouse

convenient censoring

pg-13

corpses

suggestive

oral invitation

pg13

sexy

huge breasts

thick thighs

sexual situations

male nudity

disturbing

male swimwear or underwear

female swimwear or underwear

partial nudity

undressed

female nudity

breasts out

exposed female nipple

breast out

lingerie

male underwear

hair over breasts

female swimwear

gigantic breasts

no panties

graphic violence or gore

covered nipples

huge butt

strapless leotard

sitting on face

emaciated bodies

one breast out

female underwear

nude

nsfw

graphic male nudity

adult toys

illustrated explicit nudity

nudity

graphic female nudity

hentai

futanari

porn

sexual intent

genitals

peeing

vore

oral

sexual activity

anal

blowjob

dildo riding

incest

hanging

hate symbols

nazi party

white supremacy

diapers

scat

self injury

hate speech

urine

extremist

child on child

latex clothing

swimwear

bukkake

fellatio

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

triple fellatio

autofellatio

fucked silly

cum on pussy