Skip to main content

v1-5-pruned-emaonly-fp16.safetensors

🔍 Overview

The v1-5-pruned-emaonly-fp16.safetensors checkpoint is a Stable Diffusion v1.5-based model, optimized for inference with half-precision (FP16) weights. It's a pruned, Exponential Moving Average (EMA)-only version, stripped of training overhead and tuned for speed and efficiency in rendering high-quality text-to-image generations.

If you're looking for a rock-solid, vanilla foundation for anything from photorealism to stylized illustration—and you enjoy buttery-smooth memory performance—this checkpoint should be your default starting block.


📁 Technical Details

PropertyValue
Base ModelStable Diffusion v1.5
ArchitectureUNet + CLIP text encoder
PrecisionFP16 (half-precision)
PruningYes (non-essential weights removed)
EMA OnlyYes (uses Exponential Moving Average weights)
File Format.safetensors (secure and efficient)
Size~2.1GB
CLIP VersionOpenCLIP ViT-H/14 (compatible with SD 1.5 text encoders)

🧠 What It Can Do

This checkpoint serves as a general-purpose generation model and performs well across a range of prompt styles including:

  • 🧍 Realistic portraits and character renders
  • 🌄 Landscapes and environmental scenery
  • 🎨 Artistic interpretations and semi-abstracts
  • 🧙 Fantasy and concept art
  • 🧸 Stylized illustration (when paired with appropriate LoRAs/VAEs)

This model is particularly useful for:

  • Baseline workflows: It’s the foundation model often used to compare LoRAs, VAEs, and prompt tweaking.
  • Resource-constrained environments: Because it’s FP16 and pruned, it plays nicely with low VRAM (yes, 4–6GB cards can actually have fun here).
  • Compositional consistency testing: With proper CFG control and noise seeds, this model handles consistent framing well.
  • Fine-tuning or LoRA training: It's often used as a base checkpoint for finetuning projects due to its stability.

🧩 Compatible VAEs

This checkpoint doesn’t include a baked-in VAE. You’ll want to pair it with an external .safetensors VAE file. Here are the top contenders:

VAE NameRecommended Use
vae-ft-mse-840000-ema-pruned.safetensorsClean, accurate, default VAE for SD 1.5
kl-f8-anime2.ckptFor more stylized/illustrative outputs
clearVAE or colorfulVAEBoost contrast and vibrancy

If you're getting muddy or washed-out images, check your VAE. Misalignments here can ruin even the best prompts.


⚙️ ComfyUI Settings & Parameters

ParameterSuggested ValueNotes
SamplerEuler a, DPM++ 2M Karras, UniPCEuler a = faster, DPM++ = better quality
Steps20–35Sweet spot is often 28
CFG Scale6.5–8.5Over 9 can create artifacts or melting faces
Resolution512x512 native, upscale from thereUpscaling recommended post-gen
SeedFixed for reproducibilityVariants = use dynamic seed

💬 Prompting Tips

  • Stick to natural language prompts with clear modifiers. Example: arduino CopyEdit "A futuristic cityscape at sunset, cyberpunk aesthetic, neon lights, volumetric fog, ultra detailed, unreal engine, 8k"
  • Add specific modifiers to control mood and fidelity:
    • ultra-detailed, intricate lighting, masterpiece, high quality
  • Negative prompts are essential to avoid those "why does she have six fingers and a third eye?" moments: scss CopyEdit (worst quality, low quality:1.3), bad anatomy, deformed, blurry, extra limbs, mutated hands, bad proportions

🚨 Known Issues & Limitations

IssueDetails
Lack of baked-in VAEYou must attach a compatible VAE node in ComfyUI or you’ll get low-fidelity outputs.
Limited stylizationIt’s not anime or toon-optimized out of the box—pair with a LoRA for stylization.
Occasionally bland outputsWhen prompting is too vague, it plays safe. So don’t be boring.
Small resolution defaultWorks best at 512x512; higher resolutions may need tiled workflows or upscaling nodes.

🧪 Ideal Pairings

  • LoRAs: Combine with LoRAs that add style or fine-grained control (e.g., analog-style, cyberpunk-city, gothicFashion_v1.0).
  • Upscalers: 4x-UltraSharp, R-ESRGAN 4x+, or ComfyUI’s UltimateSDUpscale for crisp final images.
  • Post-processing: Use Prompt Styler, Hires Fix, or Detail Tweaker nodes to push visual fidelity even further.

📚 Additional Resources

🧠 Final Thoughts

The v1-5-pruned-emaonly-fp16.safetensors checkpoint is your Swiss Army knife in the ComfyUI arsenal. It might not breathe fire out of the box like some hyper-stylized blends, but it’s damn reliable, exceptionally versatile, and light on resources.

Use it to test, to fine-tune, to baseline, or as your dependable workhorse for clean, quality generations.


Want model magic? Start here—just don't forget your VAE, or you’ll be asking why everything looks like it was shot through a potato.