majicMIX_realistic_v6-mnn

majicMIX Realistic v6 (MNN)

This repository provides an MNN-format conversion of emilianJR/majicMIX_realistic_v6 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):

Model Provenance

Conversion settings

python convert_hf_to_mnn_sd.py \
    --model emilianJR/majicMIX_realistic_v6 \
    --out ./out/majicMIX_realistic_v6 \
    --size 512 \
    --unet-bits 8 \
    --unet-block 32 \
    --clip-bits 8 \
    --vae-bits 8 \
    --img2img \
    --zip --zip-name majicMIX_realistic_v6-int8-block32-img2img

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

Output files

clip_v2.mnn                 0.13 MB
clip_v2.mnn.weight        148.92 MB
model.json                  0.00 MB
pos_emb.bin                  0.23 MB
token_emb.bin               72.38 MB
tokenizer.json                2.12 MB
unet.mnn                     1.13 MB
unet.mnn.weight           911.38 MB
vae_decoder_fp16.mnn         0.22 MB
vae_decoder_fp16.mnn.weight  94.38 MB
vae_encoder_fp16.mnn         0.17 MB
vae_encoder_fp16.mnn.weight  65.15 MB
TOTAL                     1296.21 MB

img2img support

This model includes a VAE encoder (vae_encoder_fp16.mnn) in addition to the usual text-to-image components, and model.json declares "img2img": true. The encoder outputs (latent_mean, latent_std); noise sampling and scaling_factor application are left to the runtime.

Note: nezumi-ai-sd-cli and the current nezumi-ai Android app do not yet implement img2img — this file is included ahead of that runtime support landing. Text-to-image works today; img2img is a forward-compatibility placeholder.

License

• Original model license: CreativeML Open RAIL-M (full text) — all credit for the weights and training goes to the original majicMIX Realistic author, as packaged for diffusers by emilianJR.
• 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: earlier majicMIX Realistic versions (v3/v4) were merged with ChilloutMix, which carries additional commercial-use restrictions. This conversion is based on v6, distributed by emilianJR under a plain creativeml-openrail-m tag with no additional restrictions noted. If you rely on this for commercial use, we recommend independently verifying the current license status of the upstream repository.

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)

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 majicMIX_realistic_v6-int8-block32-img2img.zip C:\sd-model

Then run:

nezumi-ai-sd-cli "C:\sd-model" "RAW photo, portrait of a young woman, natural lighting, film grain" --steps 25 --width 512 --height 640 --backend cpu --out out.png

Options

The original author recommends euler for close-up shots and eulera for everything else, and suggests using an After Detailer / face-restoration pass rather than relying on the model's built-in face fixing. CFG 5–7 with 25–30 steps is a reasonable starting point.

Roadmap

• Linux build of nezumi-ai-sd-cli
• macOS build
• img2img support in nezumi-ai-sd-cli / Android app runtime
• SDXL support
• Additional quantization variants

Disclaimer

This is an unofficial, community conversion and is not affiliated with or endorsed by the original majicMIX Realistic author or by emilianJR.