ngosangns Knowledge Base

Image Generation

#technology#image-generation#stable-diffusion#text2image

Updated: 2026-09-24

Source

This note gathers AI image generation and editing tools, models, and prompt material in one place. The main list covers text-to-image services and a few larger entries that go deeper, such as getimg.ai, FLUX.1 Kontext, and Meshy.ai for 3D output. Shorter lines point to design sketching, virtual try-on, relighting, and image editing tools. A second section collects Stable Diffusion resources, including checkpoints, LoRA repositories, web UIs, prompt guides, and Vietnamese documentation. Prompt templates and a long negative prompt for hands sit under a third section, alongside a ComfyUI tool for visual novel sprites. The last section lists models and embeddings for an NSFW setup. Treat it as a reference shelf rather than a tutorial.

Image Generation Tools

  • Text to image:
    • https://stockimg.ai #text2image
    • https://www.unstability.ai #text2image
    • https://stablecog.com/generate #text2image
    • https://github.com/jakowenko/phrame #text2image
    • https://imgcreator.zmo.ai #text2image
    • https://designer.microsoft.com #text2image
    • https://www.shakker.ai #text2image
    • https://gamma.app
    • getimg.ai: All-in-one AI platform for generating and editing images and video
      • Generate images/video from a text description in under 60 seconds, with no prompt-engineering knowledge required
      • Supports 20+ languages
      • Access to 25+ leading AI models (FLUX, Sora, Kling, GPT Image, Gemini) with a single subscription
      • Editing features: add objects, restore old photos, change backgrounds, upscale resolution
      • Create consistent content using reference images
      • Team collaboration with a shared workspace
      • Source: https://getimg.ai/ #text2image #image-editing #AI-platform
    • FLUX.1 Kontext: A suite of generative flow matching models for image generation and editing with in-context generation. Supports character consistency, local editing, style reference, and iterative editing. Inference is up to 8x faster than leading models. Models: FLUX.1 Kontext [pro] (a pioneer for fast, iterative editing), [max] (improved prompt adherence and typography), [dev] (open-weight 12B). Among the top performers on KontextBench. Website: https://playground.bfl.ai #text2image #image-editing #in-context #FLUX
    • Meshy.ai: AI tool that creates 3D models from text or images in seconds
      • Features: Image to 3D, Text to 3D (multilingual), AI Texturing (PBR maps for Unreal, Unity, Blender, Maya, WebGL), Animation (automatic rigging), 3D to Video, Smart Remesh, Text to Image
      • Production Ready: Asset management, private licensed, multiple 3D file formats (FBX, GLB, OBJ, STL, 3MF, USDZ, BLEND), resize and pivot tool, multiple concurrent tasks (50+)
      • Workflow Integration: REST API, plugins for Blender, Unity, 3ds Max, Maya, Godot, Unreal Engine, Bambu Studio
      • Enterprise Features: Multi-team management, shared workspace, ISO27001/SOC2 Type II/GDPR certifications, SSO, increased data privacy, dedicated support, forever asset retention
      • Use Cases: Film Production (VFX, previsualization), Product Design, Education, Game Development, 3D Printing, VR/AR, Interior Design, E-commerce, Toy Design
      • Benefits: 10x faster than traditional methods, up to 100x cost reduction, no specialized modeling skills needed
      • Website: https://www.meshy.ai/ #3D-generation #text-to-3D #image-to-3D #AI-modeling
  • Design sketching: https://www.visily.ai #design
  • Change a model's outfit (virtual try-on): https://huggingface.co/spaces/yisol/IDM-VTON #clothing
  • IC-Light (Relighting with Foreground Condition) - Relight an object based on the background: https://huggingface.co/spaces/lllyasviel/IC-Light #relighting
  • Dress a model in clothes:
  • Image editing:
  • MediaPipe: Google AI Edge's cross-platform machine learning solutions, customizable for live and streaming media. Provides real-time multimedia processing solutions such as face detection, hand tracking, and pose analysis - GitHub #media #computerVision #realTime

Stable Diffusion

Other Image Generation Models

  • FLUX.1 Kontext: A suite of generative flow matching models with in-context image generation and editing capabilities.

Midjourney

Stocks

  • Civitai | Stable Diffusion models, embeddings, LoRAs and more: https://civitai.com #stablediffusion #models

Stable Diffusion Prompts & Tools

Interview Prompt Template

You are conducting an interview for a [Role/Job Title] role. I want you to ask me [Question Difficulty] [Topics/Languages] interview questions. Your response should contain the difficulty rating, but do not give me the answer or any other information. Start by asking me one question.

Stable Diffusion Visuals

Control the Camera

Negative Prompt for Hands

ng_deepnegative_v1_75t,(worst quality, low quality:2), monochrome, zombie,overexposure, watermark,text,bad anatomy,bad hand,extra hands,extra fingers,too many fingers,fused fingers,bad arm,distorted arm,extra arms,fused arms,extra legs,missing leg,disembodied leg,extra nipples, detached arm, liquid hand,inverted hand,disembodied limb, oversized head, extra body, extra navel, easynegative, duplicate, ugly, huge eyes, text, logo, worst face, (bad and mutated hands:1.3), (blurry:2.0), horror, geometry, bad_prompt, (bad hands), (missing fingers), multiple limbs, bad anatomy, (interlocked fingers:1.2), Ugly Fingers, (extra digit and hands and fingers and legs and arms:1.4), ((2girl)), (deformed fingers:1.2), (long fingers:1.2),(bad-artist-anime), bad-artist, bad hand, extra legs ,(ng_deepnegative_v1_75t), squint eyes, jeans, sitting,

Additional Tools

NSFW Generation Setup

Prepare models:

LoRA & Textual Inversion:

Supporting websites & software:

  • Posemy.art
  • Photoshop, Clip Studio Paint

See also: SUAPP AI · Video Generation · 3D Models · Content And Multimedia Tools