golden boy low wan — Model AI WAN

Wan 2.2 14B V1 whats new: -This is the same dataset + captions from the 2.1 lora, except trained on both the high and low WAN 2.2 14B models. -You will get all the benefits of the upgrade from 2.1 to 2.2. Especially movement and camera control is quite nice. -Warning: I feel its gotten further away from the dataset in terms of style, I will try doing more training later, I think its in good enough state now to release. I wanna move onto something new next, this update was more about learning how to train 2.2. Read below about the training for my process which is new. What is this lora? This is a style lora used to recreate the style of the 1995 anime series "". The series has beautiful mid-90s matte painting style backgrounds which came out great in the lora. And the way they draw the girls is awesome and really represents the art style of the period for raunchy comedies. But if you just want a mid-90's retro style anime look in wan then use this lora too, its really great at just doing older style anime in general. And it is perfect at doing detailed environmental shots. Its captioned on bikes, cars, delicious looking food, garbage etc, not just people. Its trained on the T2V model and therefore should also work for I2V. Trigger word: Goldenboystyle (You do not need to add any other descriptions for anime or animation style in the prompt, it should make it the style without any other prompting). In fact I would recommend against adding anime keywords to the prompt as it will create more of a bias from the base model which is now trained on anime much better than before. The trigger word may not even be needed but I put it in anyway. All the characters from the show is in the training data. The blonde woman (Madame President) comes out pretty much if you mention blonde women. If you describe any character from the show it will probably generate them accurately. The main character Kentaro Oe will also come out if prompted but only by description and not by name. The silly faces the characters make are also in the training data. There is naked breasts in the training data but no lower genitals. Recommended Settings It can run on default wan workflow just fine, and retains that real nostalgic retro animation style, but I recommend to mix this lora with the following optimization loras. There is 3 settings I recommend and each has their own positives and negative effects. It's too early to tell whats best aside from default. I am leaning on the 2.1 light lora because 2.2 kills the motion so hard and also changes the style to be less like the show, but still a nice retro feeling. I think I will make a workflow for my loras and link that from now on. So just download my example workflow for this lora and try it yourself. See below image to see how it effects the look. For motion check the example generations I provided for these, it has in the comments the settings I used for reference. LINK TO EXAMPLE WORKFLOWS 1.) Default Setting Just run the lora with no other loras and it will work fine. And it will retain the closest look and feel to the original source material. On a 3090 it takes over 20 mins for a 720p video to generate. 20 steps (10/10), 3.5 CFG, NO NAG Benefits: Closer to trained data. You get all the 2.2 benefits like motion, quality, camera control etc. Negatives: Slower, more resource intense 2.) Lightx2V Wan 2.1 Lora Optimization 1.) This lora (golden boy style) (strength 1.0 on both high and low) 2.) 7 Steps ( 3 / 4), though you can try 4/4 or 2/2. CFG 1 with NAG Benefits: Can complete higher resolution with fewer steps. The motion is retained and style closer default than lightning lora. Negatives: Lightx2V is a Wan 2.1 lora so I think you downgrade the output to look more like 2.1 than 2.2. I feel also that the colors are a bit dark. It adds some weird snow effect sometimes which can be mitigated by increasing strength on the lightx2v loras. 3.) Lightning 1.1 Wan 2.2 Lora Optimization 7 Steps ( 3 / 4), though you can try 4/4 or 2/2.CFG 1 with NAG 1.) This lora (golden boy style) (strength 1.0 on both high and low) 2.) Benefits: Can complete higher resolution with fewer steps. It kinda makes colors brighter and less saturated if you like that aesthetic. Its a 2.2 lora so you technically get benefits from 2.2 wan Negatives: It effects the style heavily, it still looks anime retro but the colors are brighter than the source material. The motion is HEAVILY reduced. 4.) Other 2.1 loras - - - 2.1 Goldenboystyle lora. You can mix this on high or low, maybe low is better. These above two loras were great for 2.1 version of this. I don't use them because I feel the more 2.1 lora you use the less the output looks like 2.2 and just becomes wan 2.1 again... If they release 2.2 versions of these loras I will edit here. See the below example to see how each setting effects the output compared to the source. In the end, I don't think there is a right choice as they all have negatives in some way, its too early to tell the best way to set things. So I'll update this bit in the future if I figure anything out. The motion killed in #3 makes me use #2 most often. And I don't have much patience for option #1. Please tell me if you have a good setting suggestion. Training Info Low Lora Model: [model] type = 'wan' ckpt_path = '/data/trainingstuff/wan2.2_base_checkpoint/low_noise_model' transformer_path = '/data/trainingstuff/wan2.2_base_checkpoint/low_noise_model' dtype = 'bfloat16' transformer_dtype = 'float8' timestep_sample_method = 'logit_normal' blocks_to_swap = 8 min_t = 0 max_t = 0.875 [adapter] type = 'lora' rank = 32 dtype = 'bfloat16' [optimizer] type = 'adamw_optimi' lr = 2e-5 betas = [0.9, 0.99] weight_decay = 0.01 eps = 1e-8 High Lora Model: Basically same settings as lora except max/min_t changes 0.875 to 1 range. type = 'automagic' lr = 2e-5 weight_decay = 0.00195 lr_bump = 5e-6 eps = 1e-8 Lets talk graphs: Here is t

Kata pencetus

GoldenBoyStyle

3,459 muat turun · 370 suka di Civitai

SHA256

031E0F0805F760BA2CCA382D8086427F89A426F1C727CB1ADAFAD9C84E43CF43

ID Model ModelTrends.ai

#25733

Laporkan kandungan

Contoh render

Prompt dan tetapan yang dikongsi oleh orang yang membuat render ini di Civitai. Pilih render untuk melihat cara ia dibuat.

Dapatkan prompt ini

Render oleh tazmannner379 di Civitai

Laporkan

Tetapan

Saiz

720x1248

Prompt

Goldenboystyle. a young man with short dark hair, red baseball cap backwards, light pink collared short-sleeved button-up shirt open at collar, dark blue jeans, white sneakers, red backpack, riding magenta bicycle with black handlebars and tires, pedaling rapidly; multi-lane asphalt highway with white lane markings, silver metal guardrail on left, overhead streetlights, green rolling hills in distance under bright clear blue sky with sparse white streaky clouds; red sports car to right slightly ahead, light blue van entering from right overtaking both; START: wide low-angle full shot tracking forward with cyclist centered; MOVE: fast lateral swoop to his right side with slight arc pan, no push-in; END: semi profile side view, close medium shot from shoulders up, camera matching his speed; strong parallax from passing vehicles, wheel motion blur, heat shimmer; warm midday light, sunlight glints on chrome, shallow depth of field at end frame, depth compression maintained

Render oleh tazmannner379 di Civitai

Laporkan

Tetapan

Saiz

720x1248

Prompt

Goldenboystyle, a young woman with shoulder length retro bob style blue hair tied with red ribbon accents walks down a sunlit stone staircase in a town. Her straw hat tips from the wind and she holds the brim with one hand to keep it in place. Her light yellow sundress ripples with each step and lifts in the breeze to reveal her thighs. She smiles with blushing cheeks as she moves her other hand down to hold her dress. She closes her eyes and turns her head slightly. A small black cat follows behind her along the steps with its tail wagging. Butterflies flutter around and flowers sway heavily at the edges of the frame while leaves rustle and blow past the front of the frame in the wind. Overhead the sky is vivid blue as large clouds move quickly out of frame. The shifting shadows cast on the ground from the foliage above dance with the wind. Warm daylight with sunny lighting and soft colors fills the scene, captured in a medium tracking shot with a subtle upward tilt and smooth camera glide.

Render oleh tazmannner379 di Civitai

Laporkan

Tetapan

Saiz

1248x720

Prompt

GoldenBoyStyle. A gothic lol1lita magical girl with frilled black and white dress and lace ribbons stands in a field of wilted dying sunflowers under a gentle breeze spinning her ornate staff before slamming it to the ground as a rainbow energy wave radiates outward the sunflowers instantly revive stand tall and bloom brilliantly all turning toward her determined expression daylight sunny lighting warm colors dynamic medium shot pulling out to a wide shot smooth sweeping camera movement

Render oleh tazmannner379 di Civitai

Laporkan

Tetapan

Saiz

1248x720

Prompt

Goldenboystyle. A young woman in a plaid skirt and oversized headphones with an antenna walks barefoot through shallow water, holding her shoes. Vibrant koi swim around her ankles, and a black cat peeks from her backpack, swatting at a butterfly. She is facing away from the camera as the tunnel ahead reveals two large green eyes blinking in the dark. Suddenly, a massive cat with soft fur bursts from the shadows and sprints outward. The camera pans left as she turns around, wide-eyed, raising her arms in surprise. The shot then shifts into a tracking movement as she begins to chase, but then she stops and turns fully to face the camera. Her eyes are bright and excited as she watches the cat run past her. Ripples spread at her feet, lily pads sway nearby, and a faint red signal light pulses near the edge of the tunnel. The moment is captured in a full shot with a long lens, using natural side lighting, soft contrast, eye-level framing, and reflective water across the tunnel surface.

Render oleh tazmannner379 di Civitai

Laporkan

Tetapan

Saiz

1248x720

Prompt

Goldenboystyle, a quiet rural evening scene at the edge of a wide rice field under a moody blue sky, a young man in a red backwards cap, light teal button-up shirt with rolled sleeves, cargo pants and work gloves stands next to a stationary parked mountain bike with a satisfied look, a shy girl in a yellow school blazer and pleated grey skirt walks up to him from behind, her long chestnut hair swaying in the breeze as she steps forward and wraps her arms around him, resting her cheek against his shoulder, the man's face goes red and his eyes go wide and freezes in place, overwhelmed, the soft wind moves their hair and distant clouds drift past green hills in the backdrop, warm dusk light reflects gently off the scene

Render oleh tazmannner379 di Civitai

Laporkan

Tetapan

Saiz

720x1248

Prompt

Render oleh tazmannner379 di Civitai

Laporkan

Tetapan

Saiz

1248x720

Prompt

Render oleh tazmannner379 di Civitai

Laporkan

Tetapan

Saiz

1248x720

Prompt

GoldenBoyStyle. three young women stand in a graffiti marked subway car glowing with glitchy neon lights, then turn away from the camera and begin walking down the aisle in sync, arms swinging and jackets fluttering with confident rhythm; the first has long red hair and wears a short sleeved black crop top with a lightweight black jacket, a silver O ring choker, and amber tinted sunglasses hanging from her chest, her eyes narrowed and lips curled into a sly smile as she glances over her shoulder and flashes a peace sign; the second wears an oversized red graphic t shirt under a loose black hoodie, round glasses, and a small crossbody bag, her brown hair in short twin buns, she swings around a vertical pole with relaxed confidence, her face calm until her eyes slowly shift sideways with a slight upward smirk; the third in the back has fluffy pink hair and chews gum, wearing a loose white bomber jacket slipping off one shoulder, a black strap top underneath, and black mini shorts with sheer tights, a long green bag strap crossing her chest, she looks straight ahead with half lidded eyes, then turns slightly and blows a large bubble that pops as she raises her brows and softly blinks at the viewer; camera trails low behind them as their hair bounces and the subway car sways, bright colors,

Model serupa

Model AI untuk penjanaan imej, video dan teks

golden boy low wan ialah LoRA untuk keluarga Wan yang disenaraikan di ModelTrends.ai, katalog baca sahaja untuk model AI imej, video dan teks sumber terbuka. Bandingkannya dengan model Wan lain, semak skor habanya untuk melihat trendnya, dan bukanya di PirateDiffusion atau BitVector untuk mencubanya.

Lagi model Wan Lagi LoRA Wan video anime retro artstyles style

Layari mengikut keluarga model