MOSSKVA — MOSS-Image SFT Merge (INT8 ConvRot). ADVANCED HANDCRAFTED MERGE based on MOSS-Image SFT (5B DiT — Diffusion Transformer with Flow Matching), blending three specialized LoRAs for anatomy and raw amateur realism. MERGE RECIPE (calibrated to avoid overbaking): MysticXXX Moss V1 (NSFW & Anatomy) 0.60 | Lenovo Moss (Primary Amateur Photorealism) 0.50 | NiceGirls V2 Moss (Secondary Photorealism) 0.30. FEATURES: Hyper-realistic skin texture eliminating the plastic 3D render look — Natural amateur lighting: smartphone flash, low light, authentic colors — Uncensored anatomical understanding without forcing explicit content — Keeps casual dressed portrait capability. QUANTIZATION (INT8 ConvRot — 5.04 GB): TensorWiseINT8Layout with regular Hadamard ConvRot rotation (group 256) — Fidelity: practically identical to the original BF16 (10.05 GB), CosSim = 0.9933 — Direct GPU quantization using native ComfyUI/comfy-kitchen layouts. REQUIRED FILES IN COMFYUI: Text Encoder (models/text_encoders/): qwen3.5_9b_w4a8_gptq.safetensors (CLIPLoader, type: moss_image) — VAE (models/vae/): flux2-vae.safetensors (VAELoader to VAEDecode) — Empty Latent: EmptyFlux2LatentImage (channels=128, downscale=16x). RECOMMENDED SETTINGS (Standard SFT): Steps 30-50 (ideal 35) — CFG Scale 3.0-4.0 (default 3.0) — Sampler: euler or dpmpp_2m_sde — Scheduler: sgm_uniform or beta — Resolution 1024x1024 / 896x1152 — Model Sampling Shift 5.0 (AuraFlow / Flow) — Average time on RTX 5060 Ti: 8-15 sec per image. PROMPT TRIGGERS FOR AMATEUR REALISM: "candid amateur phone photo, casual selfie taken with an iPhone/Samsung" — "dim room lighting, direct flash photography, authentic harsh shadows" — "natural uneven skin texture, subtle skin imperfections, visible pores, no makeup" — "spontaneous pose, slightly grainy film look, messy background, candid snapshot". AVOID in positive prompt: masterpiece, 8k, hyperrealistic, octane render, flawless skin, cinematic lighting (forces artificial smooth video-game skin). VERSIONS: mosskva 1.0 (INT8 ConvRot, this version, 5.04 GB) — mosskva 1.0 (W6A8 ConvRot, 4.21 GB) — mosskva 1.0 (NVFP4 Hybrid, 4.20 GB). Additional Turbo DMD2 versions (8 steps, CFG 1.0) also available in this series. LICENSE: allows use without credit, allows sharing merges, allows different licenses on merges. Commercial use allowed. Not intended to depict actual persons.
Description
MOSS-Image SFT Merge — INT8 Turbo DMD2 (ConvRot)
This is the INT8 ConvRot Turbo DMD2 edition of mosskva, built on MOSS-Image SFT (5B DiT / Flow Matching). It combines MysticXXX Moss V1 (0.60), Lenovo Moss (0.50), and NiceGirls V2 Moss (0.30), plus the 8-step DMD2 distillation (1.00) for fast generation. This checkpoint is quantized in INT8 ConvRot and is approximately 5.04 GB.
Recommended Turbo settings (ComfyUI): 6–10 steps (ideal: 8), CFG 1.0 (required; the negative prompt is not processed), sampler euler or dpmpp_sde, scheduler sgm_uniform or simple, resolution 1024x1024 or 896x1152, and ModelSampling Shift 3.0–5.0. Expected generation time is approximately 2–3 seconds per image on an RTX 5060 Ti.
For MOSS-Image, use a compatible MOSS Image text encoder such as qwen3.5_9b_w4a8_gptq.safetensors with CLIPLoader type moss_image, flux2-vae.safetensors for the VAE, and EmptyFlux2LatentImage (channels 128, 16x downscale).
Prompt tips: use candid amateur phone photo, casual selfie taken with an iPhone/Samsung, dim room lighting, direct flash photography, authentic harsh shadows, natural uneven skin texture, subtle skin imperfections, visible pores, no makeup, spontaneous pose, slightly grainy film look, messy background, and candid snapshot. Avoid masterpiece, 8k, hyperrealistic, octane render, flawless skin, and cinematic lighting when you want the raw amateur look.