🎉 New Year Sale: Get 20% OFF on all plans — Use code NEWYEAR2026.

Upgrade now
AniMesh - Animesh-Pruned V2.2 thumbnail

ModelsLab/AniMesh - Animesh-Pruned V2.2

animesh-animeshprunedv22
Text to Image Community ModelFree for Premium UsersLLMs.txt

Hi everyone.

First of all I ask you a courtesy.

If you use my models, install the ADetailer extension for your A1111.

Navigate to the "Extensions" tab within Stable Diffusion.

  • Go to the "Install from URL" subsection.

  • Paste the following URL: https://github.com/Bing-su/adetailer

  • Click on the "Install" button to install the extension

  • Reboot your Stable Diffusion

SECOND THING:
MY RECOMMENDED SETTING HAS CHANGED. Now there is image optimization even for those who cannot install the xformers module.

It all started with trying to make a new version of Aniverse, unfortunately without success (10 days of work wasted). But rather than making a version available that doesn't satisfy me at all, I prefer to do the training again.

So by playing around between one merge and another this version appeared.

Sincerely? I was amazed by it too.

I took over 650 test images to make sure.

I was initially torn on whether to release it as a new Aniverse release or a new Animesh release.

Then after thinking a little bit and, seeing that the base with the greatest weight is Animesh, I decided to release it as a new version of the latter.

The differences?

So Animesh was born mainly with the aim of representing only "girls", so, you can do something else but it is "limited".

It's also slightly more "cartoonish" than Aniverse.

MY FAVORITE PROMPT:

  • 1) (best quality, masterpiece, colorful, dynamic angle, highest detailed) upperbody shot, fashion photography, YOUR PROMPT, bokeh, light passing through hair, (abstract background:1.3), (official art)

  • 2) (masterpiece, best quality, highres:1.2), (photorealistic:1.4), (intricate and beautiful:1.2), (beautiful detailed eyes:1.2), (detailed light:1.2), (soft lighting, side lighting, reflected light), (colorful, dynamic angle), upper body shot, fashion photography, YOUR PROMPT, dynamic pose, bokeh, light passing through hair, (abstract background:1.3), (realistic skin texture:1.2), (HDR:1.3), <lora:epi_noiseoffset2:1>

Neg Prompt:

PS: Pruned will be added next week
PPS: Next version of Aniverse in 40 days... more or less... (1000 hours of training more or less)

//////////////////////////////////////////////////////////////////////////////////////////////

Ciao a tutti.

Prima di tutto vi chiedo una cortesia.

Se utilizzate i miei modelli, installatevi l'estensione ADetailer per il vostro A1111.

  • Cliccate su "Extensions" tab di Stable Diffusion.

  • cliccate su "Install from URL".

  • Incollate questo indirizzo URL: https://github.com/Bing-su/adetailer

  • Click su "Install"

  • Riavviate Stable Diffusion


//////////////////////////////////////////////////////////////////////////////////////////////

Con sorpresa per tutti, ho aggiornato Animesh dopo moltissimo tempo.

Vi chiederete come mai, immagino.

Il tutto è nato cercando di fare una versione nuova di Aniverse, purtroppo senza successo (10 giorni di lavoro buttato). Ma piuttosto di mettere a disposizione una versione che non mi soddisfa per niente, preferisco rifare il training nuovamente.

Così giochicchiando tra un merge e l'altro è apparsa questa versione.

Sinceramente? Ne sono rimasto stupito pure io.

Ho fatto oltre 650 immagini di test per esserne sicuro.

Inizialmente ero indeciso se rilasciarla come una nuova versione di Aniverse o una nuova versione di Animesh.

Poi dopo aver riflettuto e, visto che la base con maggior peso è Animesh, ho deciso di rilasciarla come nuova versione di quest'ultima.

Le differenze?

Allora Animesh è nato principalmente con lo scopo di rappresentare solo "ragazze", per cui, si riesce a fare qualcos'altro ma è "limitato".

Inoltre è leggermente più "cartoonish" rispetto ad Aniverse.

MY FAVORITE PROMPT:

  • 1) (best quality, masterpiece, colorful, dynamic angle, highest detailed) upperbody shot, fashion photography, YOUR PROMPT, bokeh, light passing through hair, (abstract background:1.3), (official art)

  • 2) (masterpiece, best quality, highres:1.2), (photorealistic:1.4), (intricate and beautiful:1.2), (beautiful detailed eyes:1.2), (detailed light:1.2), (soft lighting, side lighting, reflected light), (colorful, dynamic angle), upper body shot, fashion photography, YOUR PROMPT, dynamic pose, bokeh, light passing through hair, (abstract background:1.3), (realistic skin texture:1.2), (HDR:1.3), <lora:epi_noiseoffset2:1>

Neg Prompt:

API PlaygroundAPI Documentation

API Endpoint URL

Base URL for all API requests to this endpoint.

https://modelslab.com/api/v6/images/text2img

API Authentication

Authentication requires a valid API key included in the request. Generate and manage your API keys from your developer dashboard. Include the key in the key parameter for all API requests.

Integration Examples

Production-ready code samples for API integration

{
"prompt": "R3alisticF, hauntingly beautiful oriental necromancer, long flowing brown hair, bangs, darkly tanned skin, earrings, bone necklaces, dark eyeshadow, red lips, vibrant, front-laced transparent, filmy silk blouse, cleavage, holding skull, in a sandstone room lit by candles, High Detail, Perfect Composition, high contrast, silhouetted, chiascuro",
"model_id": "animesh-animeshprunedv22",
"lora_model": [],
"width": "1024",
"height": "1024",
"negative_prompt": "(worst quality:2), (low quality:2), (normal quality:2), (jpeg artifacts), (blurry), (duplicate), (morbid), (mutilated), (out of frame), (extra limbs), (bad anatomy), (disfigured), (deformed), (cross-eye), (glitch), (oversaturated), (overexposed), (underexposed), (bad proportions), (bad hands), (bad feet), (cloned face), (long neck), (missing arms), (missing legs), (extra fingers), (fused fingers), (poorly drawn hands), (poorly drawn face), (mutation), (deformed eyes), watermark, text, logo, signature, grainy, tiling, censored, nsfw, ugly, blurry eyes, noisy image, bad lighting, unnatural skin, asymmetry",
"num_inference_steps": "31",
"scheduler": "DPMSolverMultistepScheduler",
"guidance_scale": "7.5",
"enhance_prompt": false,
"key": "YOUR_API_KEY"
}

SDKs

Official SDKs

Production-ready SDKs and client libraries for all major programming languages

API Parameters

Technical specifications for API request parameters.

Field NameParameterTechnical Description
promptpromptprompt help in image generation
Modelmodel_idEnter model_id that can help in image generation
lora Modellora_modelNo description available
Widthwidthwidth of the image
Heightheightheight of the image
Negative Promptnegative_promptNegative prompt help in avoid things that you do not want in image
Stepsnum_inference_stepsNumber of inference steps
SchedulerschedulerSampling scheduler
Guidance Scaleguidance_scaleHow closely to follow the prompt (1-10)
enhance_promptenhance_promptAutomatically enhance the prompt