SOLORDZ MOSS Base version
Our first MOSS beta version of the model
Our settings:
Based on base model, work with 24 steps, cfg=2-3
er_sde/beta
But you can experiment with the parameters.
If you like our work and want support us please support us directly, since I am in a country which cannot get money from Civitai https://www.buymeacoffee.com/tripleheadg
Also check out our other models Triple_Headed_Monkey Creator Profile | Civitai
SolordZ_Realism_Moss_v1
This version of the model focuses on photographic realism, with an emphasis on believable faces, natural skin, coherent anatomy, and convincing materials and environments. It is suited to a wide range of photographic approaches, including casual snapshots, portraits, documentary imagery, fashion photography, and atmospheric scenes.
The goal is realism with photographic character: natural variations in skin texture, imperfect expressions, realistic fabric behaviour, and lighting that belongs to the scene. Depending on the prompt, images can range from ordinary phone photographs and direct-flash snapshots to carefully composed portraits.
Alongside the model, we developed and tested a structured six-part prompting system for describing images clearly and consistently.
This approach separates photographic treatment, period, theme, fashion, visual identifiers, and scene description. It provides a practical way to organize complex requests while keeping the main description readable.
We would also like to express our sincere appreciation to KandooAI, the creator of Juggernaut MOSS v1. This release incorporates weights from their model as part of the merging process. We greatly appreciate their work and contribution to the MOSS community.
Recommended Prompting System
1. Mode
Defines the photographic approach and the image’s overall visual character.
Include relevant framing, camera viewpoint, lighting behaviour, depth of field, focus, image texture, and processing. Examples include an available-light documentary portrait, a direct-flash compact-camera snapshot, or a softly faded colour-film photograph.
Use photographic characteristics that support the intended result. Not every image needs shallow depth of field, film grain, dramatic lighting, or extreme sharpness.
2. Era
Establishes the photographic period or aesthetic.
Examples include late-1970s colour photography, 1990s consumer film snapshots, early-2000s compact digital photography, and contemporary smartphone images.
When describing a period-inspired image, distinguish the intended aesthetic from an actual capture date.
3. Theme
Defines the main subject, activity, atmosphere, and context.
This section establishes the creative intention briefly: an interrupted conversation, a quiet domestic moment, an outdoor working portrait, or a spontaneous nighttime encounter.
4. Fashion
Defines the overall clothing category and relevant fashion influences.
Examples include practical workwear, contemporary casualwear, formal eveningwear, or vintage sportswear. Detailed garments, accessories, fabric textures, and their placement belong in the main Prompt.
5. Additional Tags
A concise, comma-separated collection of important visual anchors.
These may include subject counts, approximate age groups, actions, expressions, objects, locations, weather, and distinctive photographic effects. Keep them consistent with the detailed description.
6. Prompt
The main descriptive section, written in connected natural language.
Describe the composition, appearance, facial expression, gaze, posture, clothing, object interactions, environment, lighting, and colour relationships.
For portraits, useful details include facial proportions, eyelid position, mouth shape, hair arrangement, and the skin’s base complexion. Describe skin texture proportionately: pores, fine lines, pigmentation, and small imperfections should vary naturally across the face rather than appear equally pronounced everywhere.
For complex scenes, specify spatial relationships and limb ownership: which hand holds an object, where each arm rests, how bodies overlap, and where each subject is looking.
Separate material colour from illumination. Warm light on neutral skin, for example, is different from a naturally warm complexion. Describe reflections, moisture, fabric sheen, and surface wear where they contribute to the scene.
Why Use This Structure?
The six sections connect the overall photographic treatment with the physical details of the scene.
In our testing, this format has been useful for organizing detailed prompts and making revisions more precise. It also makes it easier to identify conflicting instructions—for example, requesting matte skin while repeatedly emphasizing glossy highlights.
The structure is a guide, not a guarantee of perfect anatomy or composition. Clear, compatible descriptions remain more useful than a large number of quality keywords.
For everyday realism, describe the qualities of an ordinary photograph: uneven framing, local differences in sharpness, modest exposure imperfections, recognizable surroundings, and natural expressions. For polished photography, specify the lighting and finish deliberately.
Recommended Sampling Settings
The following sampler and scheduler combinations have worked well in our testing:
Sampler/Scheduler deis_3m_odesgm_uniform or dpmpp_2m_sderadiance_shift
Treat these as starting points and adjust them to suit your workflow and preferred photographic result.
SolordZ_Moss Art & Anime Model
This model has been trained on a diverse collection of artistic styles, anime aesthetics, and recognizable characters, covering a wide range of visual approaches, from stylized illustrations and Japanese animation to more realistic imagery.
Alongside the model, we developed and tested a structured six-part prompting system designed to achieve clearer, more detailed, and visually consistent generations.
Rather than relying on a single collection of keywords, this approach separates visual style, artistic context, subject information, and scene description into distinct sections. This helps the model interpret complex prompts more effectively, improving composition, character consistency, anatomical accuracy, and the reproduction of fine visual details.
Recommended Prompting System
Our prompting system uses six sections:
1. Mode
Defines the visual medium and overall artistic direction.
For anime, this may include the animation studio, artist, franchise, adaptation, illustration technique, linework, cel shading, color palette, and visual effects.
For photography, it describes the photographic approach, camera characteristics, image texture, lighting behavior, and processing.
2. Era
Establishes the visual period and its associated aesthetic characteristics.
Examples include 1990s Japanese animation, contemporary anime production, vintage film photography, or modern digital photography.
3. Theme
Defines the subject, atmosphere, genre, and narrative context of the image.
This section communicates the overall creative intention without overloading the detailed scene description.
4. Fashion
Describes clothing styles, accessories, materials, and relevant fashion influences.
It helps establish the intended wardrobe while leaving precise garment placement and physical details to the main prompt.
5. Additional Tags
A concise, comma-separated collection of important visual identifiers.
This may include character names, franchises, subject counts, poses, expressions, objects, environmental elements, and distinctive visual features.
6. Prompt
The main descriptive section and the most detailed part of the system.
It describes the complete scene in natural language, including subject appearance, facial expressions, body positioning, limb relationships, clothing, object interactions, environment, composition, lighting, colors, and textures.
Particular attention is given to spatial relationships and anatomical clarity: which hand holds an object, where each limb is positioned, how subjects interact, and how foreground and background elements overlap.
The objective is to eliminate unnecessary ambiguity and give the model a precise, coherent visual description.
Why use this structure?
The six sections work together to establish both the overall visual identity and the smallest scene details.
In our testing, this approach has produced more controlled, detailed, and visually coherent results than less structured prompting.
The format is suitable for anime, illustration, character-focused artwork, and photorealistic generation.
Recommended Sampling Settings
These sampler and scheduler combinations have worked well in our testing:
Generation type Sampler/Scheduler
Anime / Illustration deis_3m_ode / sgm_uniform
Realism / Photography dpmpp_2m_sde / radiance_shift
For the realism configuration, install the following ComfyUI custom-node package:
Since this is the basic model, you can use CFG and negative prompt.
For realism, we recommend CFG=2 and 24-30 steps
for anime and art CFG=3.5 30-50 steps
Generation Quality and Workflow
All showcased images are generated directly with the model using a basic ComfyUI workflow.
No external upscalers, post-processing enhancers, detail restoration tools, or additional image improvement stages are used.
The examples represent the model's native generation capabilities rather than results enhanced through a separate processing pipeline.
For the best results, we recommend using the structured six-part prompting system described above.
SolordZ_Zero_Restart (Krea2)
Our an experimental version based on the RAW model.
It works in 8 steps and CFG=1, but the prompt needs to be written in more detail than for the Turbo version.
There are two versions available at once Int8_Convrot and FP8
ZIT/ZIB/Krea 2 project collaboration with TripleHeadedMonkey
Krea2 project
Our first TE for Krea2 - Improved prompt understanding and details TE_SoLordZ_ZImage_Krea2 - Krea2_SolordZ_TE_v1.0 | Krea 2 Text Encoder | Civitai
ZIB project
Returning after a pause.
I left Civitai for a short time due to personal circumstances. However, during my absence, together with Triple Headed Monkey, we did not stop working and conducted several major projects.
Today I decided to publish one of the very first, but at the same time strong versions of our joint development — the improved ZIT base. Key changes compared to what was before: increased detail, reduced background blurring (less blurring) and improved realism.
Thanks for waiting. We are back and ready to continue working.
We use our training data and our soft for training.
!!! For best result use this TE THM_UNC_Z-image_TE - v1.0 | ZImage Text Encoder | Civitai
We released our another uncensored TE Z_Image_TE_SoLordZ - Z_Image_TE_SoLordZ_v1 | ZImage Text Encoder | Civitai
If you like our work and want support us please support us directly, since I am in a country which cannot get money from Civitai https://www.buymeacoffee.com/tripleheadg
our WF's SoLordZ WF (upscale) - v1.0 | ZImage Workflows | Civitai
and https://civarchive.com/models/2662358?modelVersionId=2989530
for realism use euler/normal, for art sometimes better result give euler_a/normal
All images in the gallery just raw generation w/o any tricks or upscale
ZIB SoLordZ v1
ZIB SoLordZ is a new chapter in the evolution of Z—Image and our collaboration with Triple Headed Monkey. The basic Z-Image model (up to 50 steps, CFG 5-9) is flexible, but requires fine tuning. Our goal was ambitious: to keep control of the "slow" model, but to teach it to generate in 8 steps with CFG=1.
We are releasing ZIB SoLordZ, one of our first public releases in a series of improvements to the Z Image Base.
ZIB SoLordZ is designed to work in "turbo mode": 8 steps, CFG=1. Due to this, it ignores the negative prompts. Everything that you want to exclude should be written directly in a positive prompt. This is especially important for anatomy, where control is crucial.
SoLordZ Krea2 Turbo v1
Together with TripleHeadedMonkey (https://civarchive.com/user/Triple_Headed_Monkey) we present our first merged version based on the stunning Krea2 Turbo base.
We are actively working on future updates, so stay tuned! Let us know your feedback and don't forget to show us what you create. ❤️
We use er_sde/beta sampler for the first pass and euler/simple for the 2nd pass.
You can use our WF (in each image).
Description
Fast 8-step model with CFG=1.
High prompt adherence
Strong styles
Designed for speed
Anatomy control through positive prompting
About this version!
ZIB SoLordZ is a new chapter in the evolution of Z—Image and our collaboration with Triple Headed Monkey. The basic Z-Image model (up to 50 steps, CFG 5-9) is flexible, but requires fine tuning. Our goal was ambitious: to keep control of the "slow" model, but to teach it to generate in 8 steps with CFG=1.
We are releasing ZIB SoLordZ, one of our first public releases in a series of improvements to the Z Image Base.
ZIB SoLordZ is designed to work in "turbo mode": 8 steps, CFG=1. Due to this, it ignores the negative prompts. Everything that you want to exclude should be written directly in a positive prompt. This is especially important for anatomy, where control is crucial.
!!! For best result use this TE THM_UNC_Z-image_TE - v1.0 | ZImage Text Encoder | Civitai
and our another uncensored TE Z_Image_TE_SoLordZ - Z_Image_TE_SoLordZ_v1 | ZImage Text Encoder | Civitai
If you like our work and want support us please support us directly, since I am in a country which cannot get money from Civitai https://www.buymeacoffee.com/tripleheadg
Don't send us Buzz
how to use:
Scheduler Euler/beta57
8 steps, CFG=1. Instant generation without loss of control.
our WF's SoLordZ WF (upscale) - v1.0 | ZImage Workflows | Civitai
and https://civitai.com/models/2662358?modelVersionId=2989530
in this version: Improved details. Textures, light, and materials have become noticeably cleaner. The overall quality and stability is significantly higher than the original.
We call this the beginning of the path. Still not perfect, but we will continue to improve in the next releases. Keep an eye on us.
Best prompt system for ZIB version without CFG (and remember that hands or legs should be described only once in the prompt, if you try to describe hands or legs a few times in one prompt model can be confused and you got not too good result):
Category:
Digital fantasy illustration / Dark gothic character portrait
Subcategory: Elegant skeletal noble, floral macabre aesthetic, cinematic dark fantasy concept art
Era/Style:
Contemporary digital painting (2020s), high-end anime/game illustration style, painterly yet crisp linework
Common Display Context:
Fantasy game character concept, dark romance illustration, gothic art print, digital portfolio showcase
Detail Level:
Extreme macro detail on polished bone texture, ornate fabric embroidery, metallic chain links, translucent butterfly wings, and intricate floral anatomy. Sharp focus on the figure with atmospheric depth and volumetric lighting. Zero photorealism, purely stylized digital illustration finish.
Composition:
Medium shot, figure positioned slightly off-center to the right. Dynamic pose with a heavy silver chain draping diagonally across the frame. Ornate wrought-iron archway frames the left side, while a lush cluster of red peonies balances the right. Flowing white coat creates elegant negative space. Slight Dutch angle adds dynamic tension.
Visual Style:
High-fantasy digital painting, gothic romanticism aesthetic, rich impasto-like brushwork blended with crisp anime-style line art, dramatic chiaroscuro, luminous accent lighting, stylized character design, zero photorealistic rendering, authentic digital illustration finish.
Setting and Scene:
Dark mystical courtyard/garden at night. Deep midnight-blue/black background with subtle starry specks. Ornate wrought-iron archway with intricate scrollwork. Abundant red peonies and roses with dark foliage. Floating red embers/sparks and glowing cyan butterflies creating atmospheric depth. No environmental clutter — pure focus on the figure and magical ambiance.
Subject(s):
Elegant skeletal figure (undead noble/lich)
Subject Description:
Head & Face: Pristine white skull with smooth polished bone texture. Glowing molten-orange eyes with soft volumetric bloom. Crown of vibrant red peonies and roses intertwined with jagged crimson antlers protruding from the temples. Pointed elf-like ears adorned with dangling crimson bead earrings. Delicate crimson vein-like markings tracing the skull.
Torso & Anatomy: Visible ribcage and spine rendered with anatomical elegance, subtle red muscle/tendon accents between bones. Draped in a lavish white coat with intricate gold vine embroidery, deep crimson silk lining, and a decorative metallic belt. Coat flows dynamically with elegant folds.
Hands & Props: Bony hands with sharp crimson-tipped claws, stained with fresh blood (realistic wet texture). Gracefully holding a heavy silver chain that drapes across the torso and loops through the fingers. Chain shows authentic metallic weight, link detail, and subtle reflections.
Pose & Expression: Slight forward lean, head tilted with an air of melancholic elegance. Shoulders relaxed, posture conveying aristocratic stillness and quiet power.
Viewpoint:
Eye-level medium shot, slight Dutch angle for dynamic composition. Perspective emphasizes the flowing coat, chain drape, and floral framing.
Color Palette:
Dominant crimson red, pristine white, antique gold, deep midnight black. Luminous cyan/blue accents (butterflies), warm orange glow (eyes/embers). High-contrast, richly saturated, harmonious gothic palette.
Scene Objects:
Ornate wrought-iron archway, red peonies/roses with dark leaves, glowing cyan butterflies, floating red embers, silver chain, crimson bead earrings, gold embroidery details.
Lighting and Shadow:
Dramatic cinematic rim lighting separating figure from background. Soft volumetric glow from butterflies and embers. High contrast between bright white coat and dark surroundings. Subsurface scattering effect on glowing eyes and translucent flower petals. Deep, rich shadows with preserved detail. No flat or ambient-only lighting.
Texture and Edges:
Smooth polished bone, rich silk fabric with realistic fold dynamics, intricate metallic gold embroidery, delicate iridescent butterfly wings, wet blood texture on claws, ornate ironwork scrollwork. Crisp illustrative edges with painterly brush transitions.
FAQ
Comments (10)
Good day everyone,
Yesterday I downloaded and did some testing with the ZIB version. It understands the styles you request much better, which really pleased me. It also supports LoRAs, which is another plus. So unlike ZIT, this model feels much more interesting to me.
Thanks for your hard work! I think ZIB still has room to grow and evolve. ;)
@Zakman99 Thank you so much for your feedback! We're really happy to hear that you enjoyed the ZIB version and found its style understanding and LoRA support useful.
You're absolutely right — ZIB still has plenty of room to grow, and we've already planned several releases in advance. These improvements will be rolled out gradually.
ZIT also handles styles very well, especially compared to the original version, but as we mentioned before, ZIT was originally tuned more toward realism, while ZIB has always been more style-oriented.
In our later internal versions we've already made major changes, and both models have evolved significantly. Our goal is for both ZIT and ZIB to excel at realism and styles alike.
So stay tuned — there are many exciting updates ahead 😉
And once again, thank you for your support and for taking the time to share your experience with us!
@Zakman99 and for the better results use style prompt similar to this. Since our ZIB works with no cfg you need use negative prompt inside positive prompt and use more detailed description for each details:
Example prompt for ZIB (and you can use the same for ZIT, it's also works):
Style: Magical Realism / Botanical Illustration.
Concept: Nature as art. Demonstrates transparency, refraction, and organic detail.
Prompt: Magical realism illustration. A young woman with hair made of blooming glass flowers stands in a greenhouse where plants are also made of crystal and stained glass. Sunlight streams through the glass leaves, creating rainbow caustics on her skin. She wears a dress of woven vines. Her hands are tucked into her pockets or behind her back, avoiding complex anatomy. Atmosphere is bright, airy, and whimsical. Intricate details of glass petals, light refraction, and soft skin texture. Text "ZIB ZSOLD" in delicate, vine-like script font in the top left corner.
Text Overlay: "ZIB ZSOLD" (Top Left, Vine Script Font)
Negative Prompt: dark shadows, horror, extra limbs, visible hands, dull colors, realistic photography.
Or another one:
Category: 2D Digital Illustration / Studio Ghibli Homage
Subcategory: Cozy interior, magical realism, nostalgic atmosphere
Detail Level: Hand-painted anime background art, 1990s cel-animation aesthetic. Studio Ghibli interior style. Cluttered teenager's bedroom, cozy/lived-in. Posters, fairy string lights, stacks of manga, warm honey light from wooden desk lamp. Teenage girl sits cross-legged on rumpled bed reading, absorbed. Fluffy cat sleeps on pile of clothes. Between bookshelf and closet: ordinary wooden door that does not belong, paint slightly different tone. Pale blue light seeps quietly under door gap. Total normalcy with one cold impossible detail. Soft brushwork, subtle color bleeding, film grain, zero 3D render, analog warmth.
Text Overlay: "ZIB ZSOLD" in vintage typewriter font, top left corner.
Or more complicated and detailed:
Category: Digital fantasy illustration / Dark gothic character portrait Subcategory: Elegant skeletal noble, floral macabre aesthetic, cinematic dark fantasy concept art Era/Style: Contemporary digital painting (2020s), high-end anime/game illustration style, painterly yet crisp linework Common Display Context: Fantasy game character concept, dark romance illustration, gothic art print, digital portfolio showcase Detail Level: Extreme macro detail on polished bone texture, ornate fabric embroidery, metallic chain links, translucent butterfly wings, and intricate floral anatomy. Sharp focus on the figure with atmospheric depth and volumetric lighting. Zero photorealism — purely stylized digital illustration finish. Composition: Medium shot, figure positioned slightly off-center to the right. Dynamic pose with a heavy silver chain draping diagonally across the frame. Ornate wrought-iron archway frames the left side, while a lush cluster of red peonies balances the right. Flowing white coat creates elegant negative space. Slight Dutch angle (~5–8°) adds dynamic tension. Visual Style: High-fantasy digital painting, gothic romanticism aesthetic, rich impasto-like brushwork blended with crisp anime-style line art, dramatic chiaroscuro, luminous accent lighting, stylized character design, zero photorealistic rendering, authentic digital illustration finish. Setting and Scene: Dark mystical courtyard/garden at night. Deep midnight-blue/black background with subtle starry specks. Ornate wrought-iron archway with intricate scrollwork. Abundant red peonies and roses with dark foliage. Floating red embers/sparks and glowing cyan butterflies creating atmospheric depth. No environmental clutter — pure focus on the figure and magical ambiance. Subject(s): Elegant skeletal figure (undead noble/lich) Subject Description: Head & Face: Pristine white skull with smooth polished bone texture. Glowing molten-orange eyes with soft volumetric bloom. Crown of vibrant red peonies and roses intertwined with jagged crimson antlers protruding from the temples. Pointed elf-like ears adorned with dangling crimson bead earrings. Delicate crimson vein-like markings tracing the skull. Torso & Anatomy: Visible ribcage and spine rendered with anatomical elegance, subtle red muscle/tendon accents between bones. Draped in a lavish white coat with intricate gold vine embroidery, deep crimson silk lining, and a decorative metallic belt. Coat flows dynamically with elegant folds. Hands & Props: Bony hands with sharp crimson-tipped claws, stained with fresh blood (realistic wet texture). Gracefully holding a heavy silver chain that drapes across the torso and loops through the fingers. Chain shows authentic metallic weight, link detail, and subtle reflections. Pose & Expression: Slight forward lean, head tilted with an air of melancholic elegance. Shoulders relaxed, posture conveying aristocratic stillness and quiet power. Viewpoint: Eye-level medium shot, slight Dutch angle for dynamic composition. Perspective emphasizes the flowing coat, chain drape, and floral framing. Color Palette: Dominant crimson red, pristine white, antique gold, deep midnight black. Luminous cyan/blue accents (butterflies), warm orange glow (eyes/embers). High-contrast, richly saturated, harmonious gothic palette. Scene Objects: Ornate wrought-iron archway, red peonies/roses with dark leaves, glowing cyan butterflies, floating red embers, silver chain, crimson bead earrings, gold embroidery details. Lighting and Shadow: Dramatic cinematic rim lighting separating figure from background. Soft volumetric glow from butterflies and embers. High contrast between bright white coat and dark surroundings. Subsurface scattering effect on glowing eyes and translucent flower petals. Deep, rich shadows with preserved detail. No flat or ambient-only lighting. Texture and Edges: Smooth polished bone, rich silk fabric with realistic fold dynamics, intricate metallic gold embroidery, delicate iridescent butterfly wings, wet blood texture on claws, ornate ironwork scrollwork. Crisp illustrative edges with painterly brush transitions.@speach1sdef178 Thank you so much for the example prompt! I followed your advice.
More information about how to get more better results use specific prompt system I add in the block "about this version", more simple prompt system also works, but better results with more long and structured prompt
Your prompt example was incredibly helpful — the images I create now look completely different. Thank you once again; I truly appreciate your hard work.
@Zakman99 glad to help and glad to hear that it works for you, have fun 😉
@Zakman99 and you also can try use our WF's. Links on the WF's in the main description of the model. And with out TE's result will be also different, we trained it for our checkpoints
very cool model. reacts well to posing instructions, fit for high res, fast and still very flexible.
Glad to hear that you like it and thank you so much for your feedback. We ppreciate it 🙂