<h1 id="seemoss-genesis-preview">🎨 SeeMoss-Genesis Preview</h1>My anime look on a new base: MOSS-Image.MOSS-Image-SFT · ~5B DiT · Natural-language, tag &amp; JSON-layout prompting · Apache 2.0 Anime illustration · Detailed characters and backgrounds · Pixel art · ComfyUI<hr />
<h2 id="what-is-seemoss-genesis">✨ What is SeeMoss-Genesis?</h2>SeeMoss-Genesis is my personal anime model built on MOSS-Image-SFT by OpenMOSS. It is trained on the same dataset as my See-Krea2-Genesis, so the same direction carries over to a new base: detailed anime women, rich backgrounds, my own pixel-art look and Game Boy-inspired imagery.🧪 This is a Preview. It is an early release so you can try the look on MOSS-Image now. Expect updates. 🚀 Turbo is here: the <a rel="ugc" href="https://civarchive.com/models/3031179?modelVersionId=3444861">Preview-Turbo</a> version is available for fast, low-step generation (CFG 1 · 4–8 steps).<hr />
<h2 id="what-does-it-bring">🆕 What does it bring?</h2><ul><li>Anime as the natural direction. Detailed anime characters and backgrounds, with attention to both the character and the scene around them.</li><li>Two trained triggers: seesee_elf and seesee_kitsune.</li><li>My own pixel-art look. It can be requested with different phrases, including a simple pixel art cue.</li><li>Game Boy-inspired imagery. My own Game Boy captures were included in the training data.</li><li>MOSS-Image prompting. Long natural-language descriptions work best. Tag lists and JSON layouts are supported by the base model. JSON layout control is still in testing: my first tests with the Bounding Box Editor workflow follow the layout well, but boxes are a strong hint, not pixel-perfect.</li></ul>📝 About English, Japanese and manga text: MOSS-Image is strong at rendering text, and my dataset includes English and Japanese text and manga material. I have not confirmed how well readable text holds up in this Preview. Please treat spelling, lettering and longer text as something to test, rather than a promised feature.<hr />
<h2 id="trained-character-triggers">🧝 Trained character triggers</h2>These two trigger words were included during training. Use the exact spelling at the start of your positive prompt, then describe the scene, pose, clothing and lighting you want.
<h2 id="seesee_elf">🧝 seesee_elf</h2>Trigger: seesee_elfEXAMPLE 01 · SEESEE_ELFExample prompt<blockquote>seesee_elf, A single female character stands leaning against a glowing pink vending machine in a neon-lit urban alleyway. The image is rendered in a high-quality, semi-realistic digital anime style with sharp focus and vibrant color grading. The framing is a full-body vertical shot, capturing the subject from head to toe with a slight low-angle perspective. She leans her left hip against the machine, her left hand tucked into her skirt pocket, while her right hand holds a pink beverage can at chest level. Her gaze is directed forward, looking slightly past the camera. She has long, straight platinum blonde hair that falls past her waist, pointed elf ears, and large amber eyes. Her face is pale with a neutral, calm expression. Her body is slender with long legs covered in sheer black pantyhose. She wears a cropped pink blazer over a black bandeau top, a matching high-waisted pink mini skirt, and black platform high-heeled shoes with ankle straps. A black lace choker and a silver necklace with a cross pendant adorn her neck, and long black earrings dangle from her ears. The background features a wet, reflective cobblestone street and blurred neon signs, including a vertical pink sign reading "OPEN" and a purple sign reading "BAR". The vending machine displays Japanese text "ドリンク" at the top and contains rows of colorful bottles. The lighting is dominated by the intense pink glow from the vending machine, which casts a strong magenta hue over the scene and creates sharp reflections on the wet ground.</blockquote>50 steps · CFG 3 · Shift 5 · euler / simple · seed 5021 · 768×1360<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/600a7949-7a87-43a7-9f29-6388f4fa4dc9/width=1024/desc_01_ex01_seesee_elf_hq_s2_00001_.jpeg" alt="desc_01_ex01_seesee_elf_hq_s2_00001_" />
<h2 id="seesee_kitsune">🦊 seesee_kitsune</h2>Trigger: seesee_kitsuneEXAMPLE 02 · SEESEE_KITSUNEExample prompt<blockquote>seesee_kitsune, A single female character with fox ears and a large, fluffy tail sits on an ornate wooden chair, her legs spread wide apart. The scene is rendered in a high-fidelity anime style, blending digital illustration with realistic textures and lighting. The framing is a full-body shot, capturing the character from head to toe, centered within the composition. She leans forward slightly, resting her arms on the back of the chair, looking directly at the viewer with a confident, subtle smile. Her face features sharp, angular features, bright orange eyes, and long, flowing orange hair that cascades down her back. Her body is slender, with visible curves and a defined waist. She wears a black, form-fitting outfit adorned with intricate gold chains and a prominent red gemstone at the center of her chest. Her legs are clad in sheer black stockings, and she wears black high-heeled boots with gold accents. The background is a dimly lit room with a vintage aesthetic, featuring a large mirror with light bulbs, a table with candles, and a vase of red roses. The lighting is warm and dramatic, casting soft shadows and highlighting the character’s features and the rich textures of her clothing and surroundings.</blockquote>50 steps · CFG 3 · Shift 5 · euler / simple · seed 7004 · 832×1248<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/975c9b60-80b7-4818-8430-e66c8bad6b4e/width=1024/desc_02_ex02_seesee_kitsune_hq_s4_00001_.jpeg" alt="desc_02_ex02_seesee_kitsune_hq_s4_00001_" />
<h2 id="pixel-art">👾 Pixel art &amp; Game Boy look</h2>Add pixel art (or similar phrases like pixel-art style, retro handheld game screen) to your description to pull the image toward my pixel look and the Game Boy-inspired direction.EXAMPLE 03 · PIXEL ART COCKPIT<blockquote>A solitary figure sits in a command chair facing a vast spaceship viewport, rendered in pixel art with a visible grid of square pixels, a limited palette of neon blues, magentas, and reds, and hard-edged blocky shapes. The camera angle is a symmetrical, eye-level rear view from behind the pilot, looking forward into the cockpit. The figure is a dark silhouette with a rounded head, seated centrally and facing away from the viewer toward the controls. The cockpit interior is dense with angular consoles on the left and right, featuring small glowing blue screens and clusters of red, orange, and green square buttons. The large, multi-paned window reveals outer space, dominated by a large blue planet with bright rings on the left and a swirling nebula of pink, purple, and orange on the right. A small, cyan wireframe sphere floats in the nebula. The floor is dark blue with red rectangular lights, and thick, segmented pipes run along the bottom corners of the frame.</blockquote>50 steps · CFG 3 · Shift 5 · euler / simple · seed 5023 · 1248×832<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1d38c5a4-d8c8-41b8-8836-3379a80a44b5/width=1024/desc_03_ex03_pixel_cockpit_hq_s2_00001_.jpeg" alt="desc_03_ex03_pixel_cockpit_hq_s2_00001_" />EXAMPLE 04 · PIXEL ART CATGIRL<blockquote>A single adult anime-style young woman kneels in a dark, narrow urban alleyway, rendered in pixel art with a visible grid of square pixels, a limited color palette, and hard-edged blocky shapes. The camera is positioned at a low angle, looking up at the figure who is facing forward with her body angled slightly to the left. She has short, light blue hair with white highlights, large expressive eyes with pink and yellow irises, and prominent white cat ears on top of her head. She wears a black long-sleeved top, a short black pleated skirt, and black thigh-high stockings. Her legs are bent at the knees, with her thighs spread apart, and she wears brown shoes. The background features dark building walls, a glowing red lantern on the left, and scattered bokeh lights in the distance, all defined by the chunky, low-resolution aesthetic of the medium.</blockquote>50 steps · CFG 3 · Shift 5 · euler / simple · seed 4024 · 832×1248<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/ce17bba7-2707-4ef7-aae6-61abc3cdf3ad/width=1024/desc_04_ex04_pixel_catgirl_hq_s1_00001_.jpeg" alt="desc_04_ex04_pixel_catgirl_hq_s1_00001_" />EXAMPLE 05 · GAME BOY LOOK<blockquote>A blue cat character stands on a grassy ledge in a retro 8-bit video game level, rendered in Game Boy Color era pixel art with a visible coarse pixel grid, small resolution, and limited color palette. The framing is a horizontal side-scrolling view showing a light blue sky with white clouds, a distant green mountain range, and a tan sandy ground area. The blue cat faces forward with a simple closed-eye expression, positioned near small orange flowers and green bushes on the right. Floating above are two yellow, round creatures with green accents, one resting on a small floating platform and another hovering in the upper right corner. A brown wooden crate sits on the far left edge, and a blue water hazard spans the bottom left. The bottom of the screen displays a black HUD bar with white pixelated text reading "WORLD 1", a counter showing "x4", and a timer reading "T:79".</blockquote>50 steps · CFG 3 · Shift 5 · euler / simple · seed 5025 · 1152×864<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/d1961425-35f5-4915-91fe-bb1afb2a0ea2/width=1024/desc_05_ex05_gameboy_hq_s2_00001_.jpeg" alt="desc_05_ex05_gameboy_hq_s2_00001_" /><h3>🖼️ NEW: Image Edit version</h3>
SeeMoss-Genesis can now edit existing pictures with a short instruction, using the MOSS-Image Edit LoRA. Change outfits, hair colour, season or accessories while face, pose and composition stay the same. Works with Preview (25 steps, CFG 4) and Preview-Turbo (8 steps, CFG 1.5).
👉 Workflow: <a target="_blank" rel="ugc" href="https://civarchive.com/models/3031981">SeeMoss-Genesis-Workflows</a> → version Image Edit v1.0 · Edit LoRA: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MOSS-Image/resolve/main/loras/moss_image_edit_lora_rank_64_bf16.safetensors">moss_image_edit_lora_rank_64_bf16</a>
<h3>🗺️ NEW: ControlNet version</h3>
SeeMoss-Genesis can now follow the pose and composition of a reference picture with depth control (MOSS-Image color/depth adapter by <a target="_blank" rel="ugc" href="https://huggingface.co/darask0/MOSS-Image-color-depth-control">darask0</a>). The prompt decides outfit, scene and style; an optional colour map switch also keeps the room layout of the reference.
👉 Workflow: <a target="_blank" rel="ugc" href="https://civarchive.com/models/3031981">SeeMoss-Genesis-Workflows</a> → version ControlNet v1.0 · Adapter: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MOSS-Image/resolve/main/loras/moss_image_color_depth_control.safetensors">moss_image_color_depth_control</a>
<hr />
<h2 id="recommended-settings">⚙️ Recommended settings</h2><ul><li>⚡ Base (default): 25 steps · CFG 2.5 · Shift 5 · euler / simple</li><li>💎 Best quality: 50 steps · CFG 3 · Shift 5 · euler / simple</li><li>🚀 Turbo (<a rel="ugc" href="https://civarchive.com/models/3031179?modelVersionId=3444861">Preview-Turbo</a>): CFG 1 · 4–8 steps (8 recommended) · Shift 5 · euler / simple · Skip Layer Guidance off · optional Detail Refiner: latent upscale 1.5× · 8 steps · CFG 1 · denoise 0.5 (group 07 in my workflows)</li><li>Skip Layer Guidance (Base / Best quality): on, layer 22 in the negative branch (MOSS-Image default)</li><li>Resolution: around 1–2 megapixels, for example 1024×1024 or 832×1472 portrait. Width and height must be multiples of 16.</li><li>Text encoder: qwen3.5_9b_w4a8_gptq (CLIP type moss_image) · VAE: flux2-vae_small. Both are available as separate versions on this page.</li></ul>🧩 Workflows: my ComfyUI workflows are on their own page: <a rel="ugc" href="https://civarchive.com/models/3031981/seemoss-genesis-workflows">SeeMoss-Genesis Workflows</a>.<ul><li>Ultimate v1.0 — text-to-image with optional Prompt Enhancer, SFW / NSFW switch, LoRA loader, Detail Refiner and Tiled Upscale.</li><li>Bounding Box Editor v1.0 — draw boxes for characters, objects and text, and MOSS-Image builds the scene to your layout. Turbo by default.</li><li>Image Edit v1.0 — edit existing pictures with a short instruction (MOSS-Image Edit LoRA): outfit, hair colour, season, accessories.</li><li>ControlNet v1.0 — follow the pose and composition of a reference picture (depth control, optional colour map for the room layout).</li></ul>All include notes with download links and target folders for every file, and save PNGs with Civitai-readable metadata.<hr />
<h2 id="which-file">📦 Which file should I use?</h2><ul><li>BF16 (9.5 GB): full quality</li><li>fp8_scaled / int8_convrot / mxfp8 (about 5 GB): good balance. mxfp8 and fp8 are best on newer NVIDIA GPUs</li><li>nvfp4 (3.1 GB): for RTX 50-series (Blackwell)</li><li>int4_convrot (2.8 GB): smallest, for low VRAM</li><li><a rel="ugc" href="https://civarchive.com/models/3031179?modelVersionId=3444861">Preview-Turbo</a>: the same six formats (BF16 · fp8_scaled · int8_convrot · mxfp8 · nvfp4 · int4_convrot) in the Turbo version</li><li>Text Encoder and VAE: separate versions, needed for all model files (Preview and Preview-Turbo)</li></ul>I have not compared the quantized files side by side yet.<hr />
<h2 id="special-thanks">💖 Special Thanks</h2>A big thank you to <a rel="ugc" href="https://civarchive.com/user/_Fischi_">@_Fischi_</a> for taking the time to run tests with the model.<hr />
<h2 id="license">📜 License &amp; credits</h2>Based on <a rel="ugc" href="https://huggingface.co/OpenMOSS-Team/MOSS-Image-SFT">MOSS-Image-SFT</a> by OpenMOSS, released under the Apache License 2.0. Thanks to the OpenMOSS team and Comfy-Org for the ComfyUI integration.

SeeMoss-Genesis

Turbo distilled Preview of SeeMoss-Genesis. All six files: BF16, fp8_scaled, int8_convrot, mxfp8, nvfp4, int4_convrot.Settings: CFG 1, 4-8 steps (8 recommended), euler / simple, Shift 5.Optional Detail Refiner: Latent Upscale 1.5x, 8 steps, CFG 1, denoise 0.5.Needs the same Text Encoder and VAE versions as Preview.Files go in <code>models/diffusion_models/</code>.

Files with SHA256: 006ab227edf0b31f117e89bbfbe27acf65d88d260579187b1d3d10dea6a71b45