Mouserat/ReV_Animated-mnn

ReV Animated (MNN)

This repository provides an MNN-format conversion of s6yx/ReV_Animated (v1.2.2, fp16) 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
ReV_Animated-mnn-int8-block32.zip	8-bit, block size 32	~1.23 GB

Model Provenance

Field	Value
Base model	s6yx/ReV_Animated, rev_1.2.2-fp16.safetensors
Original source	Checkpoint merge by s6yx; handles anime, semi-realistic, and fantasy styles in one model
Format	MNN (clip_v2.mnn + .weight, unet.mnn + .weight, vae_decoder_fp16.mnn + .weight, token_emb.bin, pos_emb.bin, tokenizer.json)
Conversion tool	convert_hf_to_mnn_sd.py (nezumi-ai)

Conversion steps

Unlike other conversions in this collection, the upstream model is distributed as a single .safetensors checkpoint rather than a diffusers-format repository, so an extra pre-conversion step is required before the MNN conversion script can read it.

# 1. Download the fp16 checkpoint
huggingface-cli download s6yx/ReV_Animated rev_1.2.2/rev_1.2.2-fp16.safetensors --local-dir .

# 2. Convert single-file safetensors -> diffusers format
python -c "
from diffusers import StableDiffusionPipeline
import torch

pipe = StableDiffusionPipeline.from_single_file(
    './rev_1.2.2/rev_1.2.2-fp16.safetensors',
    torch_dtype=torch.float16,
    safety_checker=None,
)
pipe.save_pretrained('./ReV_Animated_diffusers')
"

# 3. Convert diffusers format -> MNN
python convert_hf_to_mnn_sd.py \
    --model ./ReV_Animated_diffusers \
    --out ./out/ReV_Animated \
    --size 512 \
    --unet-bits 8 \
    --unet-block 32 \
    --clip-bits 8 \
    --vae-bits 8

No fine-tuning or retraining was performed — weights are unchanged from the original checkpoint aside from the diffusers-format repack and the MNN format conversion/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
TOTAL                    1230.89 MB

License

• Original model license: CreativeML Open RAIL-M (full text) — all credit for the weights and merge work goes to s6yx.
• 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: this is a checkpoint merge, meaning it is derived from multiple upstream Stable Diffusion models. The RAIL-M license and its use-based restrictions apply to the merged result as distributed by s6yx.

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 ReV_Animated-mnn-int8-block32.zip C:\sd-model

Then run:

nezumi-ai-sd-cli "C:\sd-model" "1girl, fantasy knight, detailed armor, anime style" --steps 20 --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	—

Prompt order matters for this model — words near the front of the prompt carry more weight. A common structure is: content type → description → style → composition. Works well across anime, semi-realistic, and fantasy-landscape prompts.

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 s6yx.