HeroicNonsense
These are uncanny. Like, I have to watch several times to catch all the little details.
Description
Tutorial and Prompts
Music
Model: Suno v5
hypnagogic Muzak luxury elite vaporwave with 90s sophisti-pop groove. Deep glissando bassline. Spacious pads. Rhodes piano. slowed down lush erotic atmosphere. Pitch-shifting, time-stretching, chopped and screwed.Keyframe Images
Workflow Diagram:
Step 1 - Posing
Model: Realistic Pony Illustrious
Set up the character, pose, and composition during this step.
Keyframe 1 Parameters:
Set up the character, pose, and composition during this step.
Keyframe 1 Parameters:
Prompt: [[unguligrade anthro, furry]], anthro pony, (rarity, horn, smug : 1), AND [[[[horny, blushing, looking at you, inviting, freckles, bedroom_eyes, cleavage]]]], equine_hooves AND (curvy female office_siren AND female unicorn cosplayer : 1), [amateur photograph, direct_flash, at night], simple_background, blazer, office skirt BREAK [[[[mlp, 3d, dock_\(anatomy\), stupid_sexy]]]], simple_background,
Negative prompt: [[feet]], [heels, shoes],
Size: 720x1280,
Seed: 263025110,
Model: Photo_real_pony_XL_TA_excl_fp16,
Steps: 15,
CFG scale: 4,
Sampler: DPM++ 2S a,
KSampler: dpmpp_2s_ancestral,
Schedule: normal,
Guidance: 3.5,
VAE: sdxl_vae.safetensors,
Denoising strength: 0,
Clip skip: 2
Step 2 - Depth Estimation
Model:
Run the image through a depth processor to guide the next step
depth_midasRun the image through a depth processor to guide the next step
Step 3 - Detailing
Model: Pony Realism 2.2
ControlNet Model:
Use this step for lighting and detailing. Apply the ControlNet model using Step 2 as the input. I used
Keyframe 1 Parameters:
ControlNet Model:
xinsir/controlnet-depth-sdxl-1.0.safetensorsUse this step for lighting and detailing. Apply the ControlNet model using Step 2 as the input. I used
Strength: 0.15, Control Steps: 0-0.9.Keyframe 1 Parameters:
Prompt: score_9, score_8_up, score_7_up, score_6_up,
mlp, fur_tuft, anthro pony, [curvy, cleavage], rarity, blazer, skirt, fluffy, horny, hooves, dock_\(anatomy\), indoors,
Negative prompt: feet,
Size: 720x1280,
Seed: 3578840513,
Model: ponyRealism_v22MainVAE,
Steps: 30,
CFG scale: 4,
Sampler: DPM++ 2M SDE Karras,
KSampler: dpmpp_2m_sde_gpu,
Schedule: karras,
Guidance: 3.5,
VAE: Automatic,
Denoising strength: 0,
Clip skip: 2,
LoRA: CinDarEff_v1_Epoch_5_lora:0.60
Step 4: Background
Model: Google Nano Banana 2 in Google Flow
Throw together a background; helps if you sketch a mockup which leaves space for the character.
Prompt:
Throw together a background; helps if you sketch a mockup which leaves space for the character.
Prompt:
Photograph taken in 2000 with 35mm camera. Office interior of WTC 1, with windows in the background. Hazy atmospheric sunrise color grading.Step 5: Compositing
Model: Flux.2-Klein
Put the character on the background and add extra visual details.
Prompt:
Put the character on the background and add extra visual details.
Prompt:
The photograph was taken with a 35mm camera in 2000. Change the background to an office interior of Twin Towers WTC. Edit the character to stand by the chair with hand on desk. Hazy volumetric sunrise.Video Generation
Model: Kling 3.0
Input the keyframes in frames mode and link a character asset if you’ve generated one.
Input the keyframes in frames mode and link a character asset if you’ve generated one.
Prompt:
Anthropomorphic unicorn pony at her desk inside executive office in twin towers New York skyscraper. She walks across the office, her ears swivel and her tail sways. Then she sits in an office chair and adjusts her blazer. Raw live action footage. Hazy volumetric sunlight glare. Dream-like intimate atmosphere.
Final Steps
Used a video editor to splice everything together, add color grading, and enhance the framerate.
Source
not provided yet
Comments
1 comment posted