Dynamic Poses slider for Pony, Illustrious and NoobAI: more extreme angles
Topic: Models
By Captain
Published 2026-10-02
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
Euler a
Steps
30
Guidance
5
Seed
455138088
Size
1664x2432
Clip skip
2
Prompt
1girl, solo, lazypos, anime-style, delicate, dreamy,
cinematic lighting, cinematic, volumetric lighting, natural shadows,
soft and gentle colors, soft pastel colors, soft shading, detailed textures,
<lora:hololive_kaela_kovalskia_redebut:0.35> kaela20, blonde hair, red eyes, long hair, smile,
black_oversized_graphic_tee, untucked tee, jeans, white_faux_fur_coat, chunky_sneakers,
outdoors, jumping, forest, holding katana, holding sword, no gloves, bare hands,
<lora:USNR_STYLE_ILL:0.5> usnr,
<lora:WSSKX_WAI:0.3>,
<lora:TRT_IL:0.65>
<lora:Smooth_Booster_v3:0.35>
<lora:illustriousXLv01_stabilizer_v1185c:0.5>
<lora:DynamicPoseIL2att_alpha1_rank4_noxattn_900steps:2.5> dynamic pose, foreshortening, extreme perspective
Negative prompt
lazyhand, lazyneg, nsfw, (sweat:1.5), (bandana:1.5), hair ribbon, bad perspective, poor lighting, missing limbs, photo, photorealistic, realistic, realism, signature, multiple belts, scarf, jacket, blush, dust, cleavage, belt, goggles, glasses, sunglasses, ribbon bow, navel, lamppost, architecture, multiple benchs, blurry, fused fingers, missing fingers, malformed hands, trash bin, (outdoor_unit:1.5), bag, socks, rolled up pants, (gloves:1.5), power lines, transmission lines, (aircraft:1.5), (birds:1.5), drone, plane
Settings
Sampler
Euler a
Steps
30
Guidance
5
Seed
2261797492
Size
1664x2432
Clip skip
2
Prompt
1girl, solo, lazypos, anime-style, delicate, dreamy,
cinematic lighting, cinematic, volumetric lighting, natural shadows,
soft and gentle colors, soft pastel colors, soft shading, detailed textures,
<lora:hololive_kaela_kovalskia_redebut:0.35> kaela20, blonde hair, red eyes, long hair, parted lips,
black_oversized_graphic_tee, jeans, white_faux_fur_coat, chunky_sneakers,
outdoors, holding gun, no gloves, bare_hands, crouching, on one knee,
<lora:USNR_STYLE_ILL:0.5> usnr,
<lora:WSSKX_WAI:0.3>,
<lora:TRT_IL:0.65>
<lora:Smooth_Booster_v3:0.35>
<lora:illustriousXLv01_stabilizer_v1185c:0.5>
<lora:DynamicPoseIL2att_alpha1_rank4_noxattn_900steps:2.5> dynamic pose, extreme perspective
Negative prompt
lazyhand, lazyneg, nsfw, (sweat:1.5), (bandana:1.5), hair ribbon, bad perspective, poor lighting, missing limbs, photo, photorealistic, realistic, realism, signature, multiple belts, scarf, jacket, blush, dust, cleavage, belt, goggles, glasses, sunglasses, ribbon bow, navel, lamppost, architecture, multiple benchs, blurry, fused fingers, missing fingers, malformed hands, trash bin, (outdoor_unit:1.5), bag, socks, rolled up pants, (gloves:1.5)
Settings
Sampler
Euler a
Steps
45
Guidance
4.5
Seed
2109646742
Size
1280x1856
Clip skip
2
Weight used
2
Prompt
1girl, sci-fi aesthetic, cyberpunk, samurai, huge ponytail, black and white kimono, DS-Illu, off shoulder, bandaged chest, mature female, beautiful japanese girl, ((cybernetic arm)), scars, katana over shoulder, light makeup, earrings, upper body close_up, dramatic angle, proud pose, incoming attack, dynamic pose, foreshortening, extreme perspective, shinto design elements, modern technology, ink splash, rice paper, bokeh, trash blows in the wind, glowing particles,
masterwork, masterpiece, best quality, detailed, depth of field, , high detail, best quality, very aesthetic, 8k, dynamic pose, depth of field, dynamic angle, adult, aged up
Negative prompt
lowres, worst quality, low quality, bad anatomy, bad hands, jpeg artifacts, signature, watermark, text, logo, artist name, extra digits, censored, patreon username, loli, nsfw,
Settings
Sampler
Euler a
Steps
30
Guidance
4
Size
2048x3072
Prompt
1girl,
prinz eugen \(azur lane\), azur lane,
embedding:lazypos, colored lineart, flat color, beautiful face, perfect eyes, detailed eyes, mature female, long hair, straight hair, orange eyes, medium breasts, dynamic pose, dynamic angle, alternate costume, alternate hairstyle, casual, pants, heart hands, ultra-detailed, high contrast, looking at viewer, floating, solo, mole under eye, pink outline, multicolored hair, heart, mole on breast, antenna hair, black tank top, midriff peek, alternate universe, outline, two-tone hair, full body, streaked hair, hatching \(texture\), heart background, shade, tank top, thick eyebrows, light frown, white hair, high ponytail, white pants, barefoot, brown eyes, red hair, breast, thighs, mole, breasts, open mouth, feet,
very aesthetic
Negative prompt
embedding:lazyneg, embedding:lazyhand, huge breasts, huge ass, cosplay, pubic hair, blush stickers, multiple views, (simple background:1.1), white background, grey background, multiple moles, (thick eyelashes:1.15), spot color, (shiny skin:1.3),
Settings
Sampler
DPM++ 2M
Steps
25
Guidance
3.5
Seed
2004688457
Size
1280x1856
Weight used
2.5
Prompt
newanimecore, masterpiece, best quality, newest, masterpiece, best quality, amazing quality, very aesthetic, dynamic pose, foreshortening, extreme perspective, absurdres, highres, depth of field, volumetric lighting, 1girl, solo, porcelain skin, white skin, long hair, braided, bows in hair, carousel, merry-go-round, dancing around, night, lights, colourful, strong colours, long skirt, long wide sleeves, puffy shoulders, upper body
Negative prompt
(worst quality:2), (low quality:2), (normal quality:2), bad anatomy, bad proportions, poorly drawn face, poorly drawn hands, missing fingers, extra limbs, blurry, pixelated, distorted, lowres, jpeg artifacts, watermark, signature, text, (deformed:1.5), (bad hands:1.3), overexposed, underexposed, censored, mutated, extra fingers, cloned face, bad eyes
Settings
Sampler
Euler a
Steps
30
Guidance
5
Seed
3794657340
Size
1664x2432
Clip skip
2
Prompt
1girl, solo, lazypos, delicate, dreamy, high angle side view,
cinematic lighting, cinematic, volumetric lighting, ray tracing, natural shadows, clouds, blue sky,
<lora:hololive_kaela_kovalskia_redebut:0.35> kaela20, blonde hair, closed eyes, long hair,
red coat, white dress, barefoot, red jacket, long sleeves, white shirt, open clothes, dress, wide sleeves, jacket, collarbone, bare legs,
outdoors, flute, playing flute, transverse flute, sitting, on rock,
flower field, forest, stream, rock,
<lora:USNR_STYLE_ILL:0.5> usnr,
<lora:WSSKX_WAI:0.3>,
<lora:TRT_IL:0.65>
<lora:DynamicPoseIL2att_alpha1_rank4_noxattn_900steps:3> dynamic pose, extreme perspective
Negative prompt
lazyhand, lazyneg, nsfw, (sweat:1.5), bandana, hairband, bad perspective, poor lighting, missing limbs, photo, photorealistic, realistic, realism, signature, multiple belts, scarf, blush, dust, see-through
N4Talent's Dynamic Poses slider pushes characters into dynamic poses, foreshortening and extreme perspective. Learn its weight, trigger phrase, scheduling advice and ideas for action illustration.
Overview
Dynamic Poses slider (PonyXL and Illustrious/NoobAI builds) is a slider
LoRA
by N4Talent that makes poses more dynamic and angles more extreme. The suggested trigger phrase is dynamic pose, foreshortening, extreme perspective.
The author recommends LoRA scheduling in
ComfyUI
(strong early in sampling, weaker later) to get the pose without hurting detail.
Reference
Name | Type | What it is |
|---|---|---|
Trigger | dynamic pose, foreshortening, extreme perspective | Optional but effective. |
LoRA weight | 0.5-1.2 | 0.8 default. |
Scheduling | strong early | Apply mostly in the first half of steps. |
Base | Pony / Illustrious / NoobAI | Pick the matching build. |
CFG / steps | checkpoint default |
AD

No install required - run AI models on the cloud
BitVector Prism is the easiest way to start: pick a model, type a prompt and generate in a clean web app, with nothing to configure. BitVector is also available on Discord and on the web (SpyGlass).
Step by step
- Generate a character and keep the seed.
- Add the slider at 0.8 with the trigger phrase.
- Compare; raise to 1.0 if the pose is still static.
- If detail suffers, schedule the LoRA to the first 60 percent of steps.
- Add camera angle tags (from below, dutch angle).
Examples
Action
masterpiece, best quality, 1girl, adult, solo, dynamic pose, foreshortening, extreme perspective, leaping between rooftops, cape, city at night, from below
Dynamic Poses 0.9
Sports
masterpiece, best quality, 1boy, solo, dynamic pose, foreshortening, volleyball spike, gym, motion blur, from below
Dynamic Poses 1.0
Creative idea: dance series
Same character, same seed, slider at 0.4, 0.8, 1.2: watch the pose intensify.
Tips
- Works great with action verbs (leaping, mid-swing).
- Combine with the Dramatic Lighting slider for action posters.
- Negative weights calm poses for portraits.
- Illustriouscharacter knowledge stays intact.
Troubleshooting
Anatomy breaks
Why it happens
Weight too high through all steps.
How to fix it
Schedule to early steps or 0.7.
No change
Why it happens
Static pose words in the prompt (standing, portrait).
How to fix it
Remove them; add action verbs.
AD

No install required - run AI models on the cloud
PirateDiffusion is Telegram only and built for pros: thousands of models, LoRAs and workflows driven by chat commands, with unlimited generation on a fixed price plan.
Questions
Pony or Illustrious build?
Trigger needed?
Optional; it helps.
Links and sources
Models in this guide
Written by
Captain
Related guides
Models
Xu Er Thick Paint style filter: painterly impasto texture on Illustrious
XUERYCJ's style LoRA adds thick-paint texture, complex composition and light enhancement to Illustrious images, with different looks per sampler. Learn the XUER guangying trigger, weight 0.8-0.9, hires value and sampler effects.
By Captain
2026-09-30
Models
96YOTTEA style LoRA for Illustrious: painterly color and mood
wwHEY's 96YOTTEA style LoRA reproduces the painterly, color-rich style of the artist 96YOTTEA on Illustrious. Learn the author's settings, weight 1.0, hires fix needs and ideas for painterly portraits.
By Captain
2026-09-29
Models
Nova Cartoon XL v6: western cartoon and toon styles on SDXL
Crody's Nova Cartoon XL is focused on cartoon and toon aesthetics. Learn its CFG 3-5 setting, the toon prompt template, negative list that keeps anime out and ideas for character and scene work.
By Captain
2026-10-03
Models
Aesthetic Quality Modifiers - Masterpiece for Illustrious: stronger quality tags
motimalu's Masterpiece LoRA for Illustrious strengthens masterpiece, best quality and very aesthetic so they produce visibly better composition and finish. Learn the prompt order, weight and ideas.
By Captain
2026-10-01
More guides
Models
FLUX.1 Dev: how to prompt it, best settings and creative ideas
A practical guide to FLUX.1 Dev by Black Forest Labs: natural-language prompting, guidance and step settings, LoRA stacking, text rendering and prompt ideas that play to its strengths.
By Captain
2026-09-30
Models
Stable Diffusion XL 1.0: prompts, settings and what it still does best
How to get the most out of the official SDXL 1.0 base model: native resolutions, CFG and sampler settings, the refiner, negative prompts and ideas for styles where SDXL still shines.
By Captain
2026-10-01
Models
Stable Diffusion 1.5: the classic model, prompted properly
Stable Diffusion 1.5 is still worth knowing: the right resolution, CFG and sampler, how to use its huge library of LoRAs and embeddings, and creative prompt ideas suited to a 512-pixel model.
By Captain
2026-10-02
Models
FLUX.2 Dev: prompting the newest Black Forest Labs model
FLUX.2 Dev brings larger prompts, better text, stronger realism and multi-reference editing. This guide covers the turbo workflow, guidance and resolution settings, prompt structure and ideas that use its new strengths.
By Captain
2026-10-03
Models
Qwen-Image: long prompts, perfect text and bilingual posters
Qwen-Image is the model to reach for when the words in the picture matter. Learn how to write its long descriptive prompts, render English and Chinese text accurately, set CFG and steps, and explore layout-heavy creative ideas.
By Captain
2026-09-29
Models
SDXL-Lightning: four-step generation on any SDXL checkpoint
ByteDance's SDXL-Lightning LoRA turns a 30-step SDXL render into a 4-step one. Learn the step counts, the CFG you must use, the sampler, and how to combine it with your favorite checkpoints and style LoRAs.
By Captain
2026-09-30

Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026