Diffus
Commencer
modèles/Quaintly Chaotic Comtesse - FINAL

Quaintly Chaotic Comtesse - FINAL

xperimenter
|
4/10/2026
|
12:40:07 PM
| Discussion|
0
Aucune image trouvée pour ce modèle

Prompts recommandés

1girl, shirt, solo

Prompts négatifs recommandés

watermark, username, patreon, logo, bad hands, bad fingers, poor quality, bad quality, unaesthetic, uncreative, boring, uninteresting, lowres, blurry, jpeg artifacts.

Paramètres recommandés

samplers

All schedulers and samplers supported by Illustrious, LCM

steps

12 - 40

cfg

1.5 - 6

vae

baked-in VAE - unknown

other models

Illustrious/QuaintlyChaoticComtesse_FINAL_202603132000 (d591263d62f2), lora-sdxl/dmd2_sdxl_4step_lora_fp16 (f032088e10cf), lora-sdxl/sdxl_dmd2_PSO_webui (cdf4f7e0890e), lora-illustrious/Gr@dientW@lds_v1 (91e32495997f), lora-illustrious/LightMaker (e5efc93e7e4f), lora-illustrious/XPM_Style_Lora_-_v0-1 (fe59d167f2d3), positive/lazypos (8bf3f10a7a37), lora-illustrious/minimalist_inkwash_il (a65a3c44e8ab), lora-illustrious/XPM_Style_Lora_-_v0 (ea62e48074fa)

Conseils

Experiment freely with CFG values from 3 to 6 and steps from 20 to 40 to find optimal generation settings.

Works very well with DMD2 Speed Lora (CFG: 1 - 1.5, Steps 8 - 12).

Supports practically all schedulers and samplers supported by Illustrious.

What is Quaintly Chaotic Comtesse?

Quaintly Chaotic Comtesse (QCC) is my attempt at a fully open recipe merged Illustrious model. QCC is quite a dynamic checkpoint that plays well with most loras. QCC merges the features and capabilities of a collection of models that I love.

What Tools are Used to Create QCC?

The main tool used to blend the source models is Chattiori Model Merger. The final mix is then trimmed.

What Models were Merged to Create QCC?

  1. IlluQuaint 0.8 by me

  2. Chaos v10 by @_Kav_

  3. Analog Madness XL5 by @CornmeisterNL

  4. Comtesse Raffinée v1.0 by @Chumple

Merge Recipe

  1. python merge.py WS "C:\ModelPath" "IlluQuaint_v0.8_202601040952.safetensors" "chaos_v10.safetensors" --alpha "0.5, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.5, 0.5, 0.7, 0.8, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0" --output "IlluChaos_Aggressive_WS" --save_safetensors --save_half --prune

  2. Using ComfyUI, bake in HandPatch (Unet-Only) and HD Eyes loras into checkpoint produced in Step 1.

  3. python merge.py SPRSE "C:\ModelPath" "IlluChaos_Aggressive_WS-hands_and_eyes_patch.safetensors" "analogMadnessSDXL_xl5.safetensors" --alpha "0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0.4, 0.2, 0.4, 0.6, 0.8, 1.0, 1.0, 1.0, 1.0, 1.0" --output "IlluChaos_SPRSE_Hybrid" --save_safetensors --save_half --prune

  4. python merge.py FREQ "C:\ModelPath" "IlluChaos_SPRSE_Hybrid.safetensors" "comtesseRaffinE_v10.safetensors" --alpha "0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.4, 0.6, 0.8, 0.8, 0.8, 0.8, 0.8, 0.8, 0.8, 0.8" --output "IlluChaosComtesse_FREQ_Hybrid" --save_safetensors --save_half --prune

Additional Info

  • CLIP skip: -2

  • VAE and CLIPs baked in

  • Practically all Schedulers and Samplers supported by Illustrious will work with QCC

  • CFG: 3 to 6. Steps: 20 - 40. This is just a simple guideline, please experiment by all means

  • Works very well with DMD2 Speed Lora (CFG: 1 - 1.5, Steps 8 - 12; again feel free to experiment)

I think that's it. What are you waiting for? Go generate some cool images with Quaintly Chaotic Comtesse and share it in the gallery!

Contributeur

xperimenter avatar

xperimenter

Précédent
Elle (based on Rick & Morty Anime) - V1
Suivant
Flux.2 - Pro
Utiliser ce modèle

Détails du modèle

Type de modèle

Checkpoint

Modèle de base

Illustrious

Version du modèle

FINAL

Hash du modèle

89e3ebef60

Créateur

xperimenter's avatar
xperimenter

Discussion

Veuillez vous log in pour laisser un commentaire.

Collection de modèles - Quaintly Chaotic Comtesse

Quaintly Chaotic Comtesse FINAL
CheckpointMODÈLES

Quaintly Chaotic Comtesse - FINAL

Hash court:
89e3ebef60

Images avec modèle de base

Photorealistic scene of undead characters including zombies and skeletons walking through a spooky Halloween cemetery filled with glowing jack-o'-lantern pumpkins and desiccated trees in a dark, foggy atmosphere.

Images avec experimental

A surreal, detailed depiction of a massive, battered Doomsday battleship stranded on a rocky coastline under a dramatic, dark swirling sky, combining dystopian gothic and tenebrism styles.
A glowing neon cross made of crystalline structures illuminated in purple stands suspended above a rain-soaked dystopian city street with neon signs and dark buildings.
A colossal biomechanical hybrid with glowing orange eyes looms over a lone human figure standing in a dark, eerie landscape illuminated by fiery light.
A Rauschenberg-inspired collage with distorted typography, bold colors, layered textures, and surreal, grungy, dystopian elements prominently featuring the word LOVE.
Miniature worker figures working in a surreal landscape made of meat. This is an AI generated image using Stable Diffusion.
AI generated image using Stable Diffusion of a cyberpunk woman superhero with a bob haircut, wearing a futuristic red and black suit, showcased against a neon dark background with abstract text.
Anime female superhero standing in front of a futuristic cityscape. This is an AI generated image using Stable Diffusion.
Futuristic cyberpunk android with glowing eyes, intricate mechanical parts, and a vibrant color palette. AI generated image using Stable Diffusion.
A futuristic robot with neon accents and elongated limbs stretches beneath a vibrant blue sky. AI generated image using Stable Diffusion.
A futuristic cyborg-inspired female robot with red-and-black detail, created using stable diffusion AI technology.

Images avec illustrious

Mercy from Overwatch in a white bodysuit surrounded and ambushed by screaming geese at night with contrast lighting and feathers flying around.
A blonde girl wearing a large white hat adorned with red flowers, sitting in a lush garden surrounded by yellow and red flowers, gently holding a blue bird on her finger under dappled sunlight.
A close-up portrait of a woman during blue hour, influenced by Vivian Maier's style with a cityscape backdrop, rich in cinematic color and detail.
A whimsical roasted character with a bread-like texture and a smoking head, created using Stable Diffusion AI.

Images avec semi-realistic anime

Cozy seaside studio interior seen through a rustic wooden window, featuring vintage ceramic coffee cup, seagull sketch on paper, and classic black film cameras, overlooking a turquoise water beach with flying seagulls and boats.
A cyberpunk woman with a robotic arm carefully trimming a bonsai tree inside a traditional Japanese room with wood floors and sliding doors, rendered in semi-realistic anime style.
A glass bowl on a tiled kitchen counter holding whole and halved strawberries, depicted in colored line art with anime flat colors and minimal shading.
Anime-style illustration of a young woman riding a blue motorcycle across a flat, dry desert with a bear plush attached to her backpack during sunset.
Semi-realistic anime woman dressed in a revealing dark Chinese outfit, sitting on an ornate red couch, depicted with expressive brushstrokes and abstract painting style.
A noblewoman with long silver hair in elegant white and gold attire standing on a balcony, overlooking a sprawling city with white gothic spires and glowing streets under soft afternoon light.
Anime-style portrait of a bold punk nun with green eyes, black hair, floral tattoos, colorful nails, wearing a blue habit and cross necklace against a vivid pink and yellow halo background.
Anime-style astronaut girl with a white bunny-shaped helmet, eyes closed, wearing a white futuristic cyberpunk suit with glowing green plants and neon effects surrounding her on a black background.
A semi-realistic anime-style illustration of a young woman with long black hair, sitting on a toilet in a modern, warmly lit bathroom, wearing a beige off-shoulder sweater and black shorts.
Anime-style woman with a bowl-cut hairstyle in a sharp black school uniform holding an OTs-14 Groza gun, standing amid flames and embers.