manga-readme
Local AI image-generation server for MangaREADME Generator.
Powered by HuggingFace Diffusers. Exposes an A1111-compatible REST API so the MangaREADME frontend connects with zero extra configuration.
Quick Start
pip install manga-readme
manga-readme serve
The server starts on http://127.0.0.1:7860 by default. Open the MangaREADME
frontend and select Local Server (manga-readme) as the provider.
Models
Pre-configured models (downloaded on first use):
| Alias | Architecture | Resolution | Repo |
|---|---|---|---|
| dreamshaper-8 | SD 1.5 | 512x512 | Lykon/dreamshaper-8 |
| sdxl | SDXL | 1024x1024 | stabilityai/stable-diffusion-xl-base-1.0 |
| sd15 | SD 1.5 | 512x512 | runwayml/stable-diffusion-v1-5 |
| sd21 | SD 2.1 | 768x768 | stabilityai/stable-diffusion-2-1 |
| animagine-xl | SDXL | 1024x1024 | cagliostrolab/animagine-xl-3.1 |
| realistic-vision | SD 1.5 | 512x512 | SG161222/Realistic_Vision_V5.1_noVAE |
| absolute-reality | SD 1.5 | 512x512 | digiplay/AbsoluteReality_v1.8.1 |
manga-readme serve --model sdxl
manga-readme serve --model Lykon/dreamshaper-8
manga-readme list-models
LoRA Support
Place .safetensors or .pt LoRA files in a directory and point the server
at it:
manga-readme serve --lora-dir ./my-loras
LoRAs are applied via prompt tags: <lora:name:0.7>. The frontend LoRA
picker sends these tags automatically.
GPU
A CUDA GPU with 6 GB+ VRAM is recommended. For CUDA support, install PyTorch with the correct CUDA version before installing manga-readme:
pip install torch --index-url https://download.pytorch.org/whl/cu121
pip install manga-readme
CPU inference works but is very slow.
License
MIT
1 maintainer
Metadata
1 maintainer
Release files for manga-readme 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| manga_readme-0.1.0.tar.gz | 9.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| manga_readme-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 22.0 kB
Release files / manga_readme-0.1.0.tar.gz
| Download URL | manga_readme-0.1.0.tar.gz |
|---|---|
| Size | 9.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
122d8e475ef7b2fe6f5339f935ff72d467a405240cf1138febb9bc7bb63a9485
|
|
BLAKE2b-256 checksum How to use checksums |
f126715761f4f037b9f27779ad08878e2388065d9dc01860195b3eac1b32d051
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.9
|
Release files / manga_readme-0.1.0-py3-none-any.whl
| Download URL | manga_readme-0.1.0-py3-none-any.whl |
|---|---|
| Size | 12.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e78378f0885f5a2316fe7d08c5fcdb91400ab2f99ae0f7097403784eb1103901
|
|
BLAKE2b-256 checksum How to use checksums |
cbbe0b9d2b6542f40b3376384b1f10ee0082cd6648fc88ef57bbcdca76863334
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.9
|
