Mouserat/Realistic_Vision_V6.0_B1-mnn

Realistic Vision V6.0 B1 (MNN)

This repository provides an MNN-format conversion of SG161222/Realistic_Vision_V6.0_B1_noVAE for use with the nezumi-ai image generation engine — a fully offline AI chat app for Android supporting on-device image generation.

A Windows CLI (nezumi-ai-sd-cli) is also provided for testing/debugging on desktop, but the primary target platform is Android. This model is not bundled with the app — users download it separately and individually agree to its license terms.

Platform note: nezumi-ai-sd-cli currently builds for Windows only (.exe). A Linux build is planned.

Variants

SD1.5 models are distributed in a single quantization variant (unlike the SDXL/Illustrious line, which offers int4/int8 variants):

File	UNet quantization	Size
Realistic_Vision_V6.0_B1-mnn-int8-block32.zip	8-bit, block size 32	~1.4 GB

Model Provenance

Field	Value
Base model	SG161222/Realistic_Vision_V6.0_B1_noVAE
Original source	Photorealistic SD1.5 checkpoint by SG161222, widely used general-purpose realism model
Format	MNN (clip.mnn, unet.mnn, vae_decoder.mnn, tokenizer.json)
Conversion tool	convert_hf_to_mnn_sd.py (nezumi-ai)

Conversion settings

python convert_hf_to_mnn_sd.py --model SG161222/Realistic_Vision_V6.0_B1_noVAE \
    --out ./out/int8-block32 --unet-bits 8 --unet-block 32

No fine-tuning or retraining was performed — weights are unchanged from the original checkpoint aside from format conversion and the quantization above.

License

• Original model license: CreativeML Open RAIL-M (full text) — all credit for the weights and training goes to SG161222.
• Redistribution: Permitted under the original model's license.
• Commercial use: Permitted within the terms of the RAIL-M license.
• Attribution: Required (see above).

Please read and comply with the original license before using this model.

This checkpoint inherits the original model's use-based restrictions in full (see Attachment A of the full license text), including prohibitions on use for exploiting minors, generating disinformation, harassment, discrimination, unauthorized medical advice, and law-enforcement/immigration profiling.

Note: the conversion script itself is part of the nezumi-ai project and licensed separately under LGPL v3 / a commercial license (see LICENSE.md). That license applies to the code, not to this model checkpoint.

Requirements (Android)

Item	Minimum	Recommended
Android Version	12 (API 31)	14+ (API 34+)
RAM	4GB	6GB+
Storage	3GB free	5GB+
GPU	Optional — OpenCL-capable GPU (Adreno, Mali, PowerVR)	Recommended

SD1.5 requirements are lower than SDXL/Illustrious (8GB RAM minimum) — see that model's README for comparison.

Usage

Android (primary)

Used automatically by the nezumi-ai app's image-generation feature (MNN backend, GPU/OpenCL → CPU fallback). Download/select this model from within the app; manual extraction is not required on Android.

Windows CLI (testing/debugging)

Distributed as a zip archive. Extract it before use — in PowerShell:

Expand-Archive Realistic_Vision_V6.0_B1-mnn-int8-block32.zip C:\sd-model

Then run:

nezumi-ai-sd-cli "C:\sd-model" "RAW photo, portrait of a woman, natural lighting, detailed skin" --steps 25 --width 512 --height 768 --backend cpu --out out.png

Options

Option	Description	Default
<model_path>	Path to the extracted MNN model folder	—
<prompt>	Text prompt	—
--negative <text>	Negative prompt	empty
--width <n> / --height <n>	Image size	512 / 512
--steps <n>	Sampling steps	20
--cfg <f>	CFG scale	7.0
--seed <n>	Seed (negative = random)	-1
--scheduler <name>	Sampling scheduler: euler|ddim|dpm|dpm++2m|dpm++2m-karras|lcm|eulera|unipc	dpm++2m
--backend <name>	cpu|opencl	cpu
--out <path>	Output path. .ppm always works; .png requires stb_image_write.h	—

For photorealistic results, dpm++2m-karras at CFG 3.5–5 with 25–30 steps tends to work well with this model. Adjust to taste.

Roadmap

• Linux build of nezumi-ai-sd-cli
• macOS build
• SDXL support
• Additional quantization variants

Disclaimer

This is an unofficial, community conversion and is not affiliated with or endorsed by SG161222.