CoolFace
Modelpublic

Mouserat/Realistic_Vision_V6.0_B1-mnn

sourceHugging Facecreativeml-openrail-mupdated 2mo agoView on Hugging Face
0likes
Model Card

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):

FileUNet quantizationSize
Realistic_Vision_V6.0_B1-mnn-int8-block32.zip8-bit, block size 32~1.4 GB

Model Provenance

FieldValue
Base modelSG161222/Realistic_Vision_V6.0_B1_noVAE
Original sourcePhotorealistic SD1.5 checkpoint by SG161222, widely used general-purpose realism model
FormatMNN (clip.mnn, unet.mnn, vae_decoder.mnn, tokenizer.json)
Conversion tool`convert_hf_to_mnn_sd.py` (nezumi-ai)

Conversion settings

bash
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)

ItemMinimumRecommended
Android Version12 (API 31)14+ (API 34+)
RAM4GB6GB+
Storage3GB free5GB+
GPUOptional — 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:

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

Then run:

bat
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
OptionDescriptionDefault
<model_path>Path to the extracted MNN model folder—
<prompt>Text prompt—
--negative <text>Negative promptempty
--width <n> / --height <n>Image size512 / 512
--steps <n>Sampling steps20
--cfg <f>CFG scale7.0
--seed <n>Seed (negative = random)-1
--scheduler <name>Sampling scheduler: euler\ddim\dpm\dpm++2m\dpm++2m-karras\lcm\eulera\unipcdpm++2m
--backend <name>cpu\openclcpu
--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.