Model
Trends
.ai
Model
Trends
.ai
de beste open source AI-modellen

Stable Diffusion 1.5: the classic model, prompted properly

Onderwerp: Modellen
Door Captain
Gepubliceerd op 2026-10-02
Stable Diffusion 1.5 is still worth knowing: the right resolution, CFG and sampler, how to use its huge library of LoRAs and embeddings, and creative prompt ideas suited to a 512-pixel model.
Deze pagina is nog niet vertaald en wordt daarom in het Engels getoond.

Overzicht

Stable Diffusion 1.5
was released by RunwayML and Stability AI in late 2022 and trained at 512x512. It is small, fast and sits at the center of the largest collection of
LoRAs
,
embeddings
, ControlNets and fine-tunes ever made, thousands of which are in this catalog.
Its raw output is rough compared with newer models, but with a good
negative prompt
, a fine-tuned checkpoint or a couple of embeddings it produces distinctive images quickly, and it runs on almost any GPU.

Naslag

Naam
Type
Wat het is
Prompt
tags
Comma-separated descriptors. Weights (word:1.3) and emphasis are well supported.
Negative prompt
text
Essential. lowres, bad anatomy, bad hands, text, watermark, blurry; or an embedding like easynegative.
CFG
6-9
7 is the standard; go to 5 for soft painterly results.
Steps
20-30
Euler a at 25 or DPM++ 2M Karras at 20-25.
Resolution
512-768
512x512, 512x768 or 768x512. Larger sizes duplicate subjects unless you use hires fix.
AD
Geen installatie nodig – draai AI-modellen in de cloud
BitVector Prism is de makkelijkste manier om te beginnen: kies een model, typ een prompt en genereer in een overzichtelijke web-app, zonder iets in te stellen. BitVector is ook beschikbaar op Discord en op het web (SpyGlass).

Stap voor stap

  1. Generate at 512x768 (portrait) or 768x512 (landscape),
    CFG
    7, 25 steps.
  2. Write a negative prompt first and reuse it; it matters more on 1.5 than on any later model.
  3. Add one style LoRA at 0.7 or a style embedding; 1.5 takes LoRAs very well.
  4. Enable hires fix (1.5x-2x, denoise 0.4-0.5) for the final image to reach 1024 on the long edge without doubled heads.
  5. Keep a list of the seeds you like; 1.5 is seed-sensitive and the same seed with small prompt edits is a good way to iterate.

Voorbeelden

Classic prompt

portrait of an old lighthouse keeper, weathered face, wool sweater, stormy sky behind, oil painting, dramatic rim light, (highly detailed:1.2)
Negative: lowres, bad anatomy, bad hands, text, watermark, blurry, cropped

Vintage illustration

1950s travel poster of a mountain railway, flat colors, screen print texture, bold typography space at the bottom, teal and orange

Creative idea: tiny worlds

macro photo of a snail shell that is a spiral staircase for tiny glowing people, moss, dew drops, tilt-shift, soft morning light

Tips

  • Camera words (85mm, f/1.8, bokeh) and medium words (watercolor, linocut) shift 1.5 strongly.
  • If anatomy breaks, lower CFG by one and add a hand-fixing embedding rather than piling on more negative words.
  • ControlNet
    (openpose, canny, depth) works best on 1.5 of all families; use it when you need a specific pose or layout.
  • For
    inpainting
    , pick one of the dedicated 1.5 inpainting checkpoints in this catalog instead of the base model.

Probleemoplossing

Two heads or repeated bodies

Waarom het gebeurt
Generating far above 512 on one axis.

Zo los je het op
Generate at 512x768 and upscale with hires fix instead of asking for 1024 directly.

Washed-out, grey images

Waarom het gebeurt
Missing or weak VAE in some checkpoints.

Zo los je het op
Use a checkpoint with a baked VAE, or load the standard SD 1.5 VAE; raise CFG by one.

AD
PirateDiffusion
Geen installatie nodig – draai AI-modellen in de cloud
PirateDiffusion is alleen op Telegram en gemaakt voor pro's: duizenden modellen, LoRA's en workflows via chatcommando's, met onbeperkt genereren voor een vaste prijs.

Vragen

Is SD 1.5 still worth using?

Yes, for speed, ControlNet work, and the enormous library of styles that were only ever trained for it.

Why do my images look worse than the examples online?

Most online examples use a fine-tuned 1.5 checkpoint plus negative embeddings and hires fix. The raw base model is a starting point.

Links en bronnen

Modellen in deze gids

Geschreven door
Captain

Verwante gidsen

Modellen
Waifu Diffusion: Danbooru-tag prompting for a classic anime model
Waifu Diffusion is the anime base model that taught a generation how to prompt with Danbooru tags. This guide covers tag order, quality tags, negatives, the right resolution and ideas for clean anime illustrations.
Door Captain
2026-10-01
Modellen
Ghibli Diffusion: the ghibli style token and how to use it
Nitrosocke's Ghibli Diffusion was one of the first style models for Stable Diffusion. Learn its trigger phrase, settings, how to describe scenes it can draw, and creative ideas for painterly animation-style landscapes.
Door Captain
2026-09-30
Modellen
DreamShaper 8 Inpainting: fixing and changing parts of an image
Lykon's DreamShaper 8 inpainting checkpoint replaces masked regions cleanly in a versatile semi-realistic style. Learn mask strategy, denoise values, prompting for the masked area, and ideas for creative edits.
Door Captain
2026-10-01
Modellen
Stable Diffusion v1.1: the original release, used creatively
Stable Diffusion v1.1 is the first public Stable Diffusion checkpoint, trained at 256 then 512 pixels. This guide shows what it is good for today: dreamlike textures, abstract compositions and deliberately rough, early-AI aesthetics.
Door Captain
2026-09-29

Meer gidsen

Modellen
FLUX.1 Dev: how to prompt it, best settings and creative ideas
A practical guide to FLUX.1 Dev by Black Forest Labs: natural-language prompting, guidance and step settings, LoRA stacking, text rendering and prompt ideas that play to its strengths.
Door Captain
2026-09-30
Modellen
Stable Diffusion XL 1.0: prompts, settings and what it still does best
How to get the most out of the official SDXL 1.0 base model: native resolutions, CFG and sampler settings, the refiner, negative prompts and ideas for styles where SDXL still shines.
Door Captain
2026-10-01
Modellen
FLUX.2 Dev: prompting the newest Black Forest Labs model
FLUX.2 Dev brings larger prompts, better text, stronger realism and multi-reference editing. This guide covers the turbo workflow, guidance and resolution settings, prompt structure and ideas that use its new strengths.
Door Captain
2026-10-03
Modellen
Qwen-Image: long prompts, perfect text and bilingual posters
Qwen-Image is the model to reach for when the words in the picture matter. Learn how to write its long descriptive prompts, render English and Chinese text accurately, set CFG and steps, and explore layout-heavy creative ideas.
Door Captain
2026-09-29
Modellen
SDXL-Lightning: four-step generation on any SDXL checkpoint
ByteDance's SDXL-Lightning LoRA turns a 30-step SDXL render into a 4-step one. Learn the step counts, the CFG you must use, the sampler, and how to combine it with your favorite checkpoints and style LoRAs.
Door Captain
2026-09-30
ComfyUI
ComfyUI nodes: documentation and troubleshooting
Plain-language documentation for the ComfyUI nodes people use most: what each node does, every input and output, how to wire it, the settings that matter, and the errors it throws with the fix for each one.
Door Captain
2026-06-02