datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
Krea-2-Turbo-Checkpoint-Format-Benchmark
Krea 2 Turbo ComfyUI Format Fidelity Benchmark
This release is a paired, deterministic comparison of eight Krea 2 Turbo checkpoint formats in ComfyUI: BF16, FP8 Scaled, INT8 ConvRot, MXFP8, NVFP4, INT4 ConvRot W4A4, GGUF Q8_0, and GGUF Q4_K_M. It contains 240 scored 1024×1024 images, saved float32 decoded tensors and final latents, every denoising trajectory, raw metric tables, telemetry, statistical comparisons, and reproduction code.
Main result
BF16 is the… See the full description on the dataset page: https://huggingface.co/datasets/Merserk/Krea-2-Turbo-Checkpoint-Format-Benchmark.z-image-turbo-genqwen36-mtp-turbo-kv-analysis
Qwen3.6 MTP Turbo KV Runtime Analysis
This repository is a curated analysis artifact for local Qwen3.6-35B-A3B MTP GGUF inference experiments on Windows CUDA. It compares clean MTP llama.cpp, QuinsZouls llama-next TurboQuant, and the completed subset of Atomic TurboQuant runs under a fixed 64k context, MoE CPU offload, and Unsloth-aligned sampling settings.
The raw benchmark runs included incomplete and capability-incompatible rows. This repo keeps only completed, comparable… See the full description on the dataset page: https://huggingface.co/datasets/jakeatx/qwen36-mtp-turbo-kv-analysis.sdxl-turbo-sae-labels
SDXL-Turbo SAE Feature Labels
20,480 labeled sparse autoencoder features across 4 UNet attention blocks in SDXL-Turbo, plus 50K generated images with full activation logs.
Built for latent-dance — a real-time audio-reactive music visualizer using SAE steering at 50 FPS.
Important attribution: The SDXL-Turbo sparse autoencoders/checkpoints used here were trained and released by Surkov et al. / EPFL through sdxl-unbox. This dataset does not claim authorship of the SAE training. It… See the full description on the dataset page: https://huggingface.co/datasets/hammamiomar/sdxl-turbo-sae-labels.zimage-base-vs-turbo-comparison
⚡ Z-Image Base vs Turbo 效果对比
使用相同的 prompt 和 seed,对比 Z-Image (Base) 和 Z-Image-Turbo 的生成效果。
📊 模型信息对比
特性
Z-Image (Base)
Z-Image-Turbo
模型
Tongyi-MAI/Z-Image
Tongyi-MAI/Z-Image-Turbo
参数量
6B
6B (蒸馏版)
架构
S3-DiT (单流 DiT)
S3-DiT (单流 DiT)
推理步数
28-50 步
8 步
CFG 引导
✅ (scale=3.0-5.0)
❌ (scale=0.0)
负向提示词
✅ 支持
❌ 不支持
生成多样性
⭐⭐⭐ 高
⭐⭐ 低
视觉质量
⭐⭐⭐ 高
⭐⭐⭐⭐ 非常高
RL 强化学习
❌
✅ (DMDR)
可微调 (LoRA等)
✅
❌
VRAM 需求
~16GB+
≤16GB
🖼️ 并排对比
Prompt 1: 🐆… See the full description on the dataset page: https://huggingface.co/datasets/DealayLomoi/zimage-base-vs-turbo-comparison.sdxl-turbo-rtmeXiang_Z_Image_Turbo_different_style_Images
Use lora from https://huggingface.co/svjack/Z_Image_Turbo_Xiang_Lora
Xiang different style Grid Image
Prince_Xiang_Z_Image_Turbo_glasses_Images
Use lora from https://huggingface.co/svjack/Prince_Xiang_Z_Image_Turbo_Lora
Xiang Glasses Grid Image
Xiang_Z_Image_Turbo_HairCut_ZH_Repose_Captioned
Prince_Xiang_Z_Image_Turbo_tease_images
Use lora from https://huggingface.co/svjack/Prince_Xiang_Z_Image_Turbo_Lora
Xiang Tease Grid Image
technique-images-sdxl-turboZ-Image-Turbo-Male-Model-ImagesXiang_POV_Touch_Z_Image_Turbo_Images
Use lora from https://huggingface.co/svjack/Z_Image_Turbo_Xiang_Lora
Xiang POV Touch Grid Image
Prince_Xiang_Z_Image_Turbo_different_style_Images
Use lora from https://huggingface.co/svjack/Prince_Xiang_Z_Image_Turbo_Lora
Xiang different style Grid Image
Xiang_Furry_Z_Image_Turbo_2_bind_imagesimg_sketch_sd_turboPrince_Xiang_Z_Image_Turbo_slim_images
Use lora from https://huggingface.co/svjack/Prince_Xiang_Z_Image_Turbo_Lora
Xiang Slim Grid Image
Turbo-AIXiang_Z_Image_Turbo_Tease_Images
Use lora from https://huggingface.co/svjack/Z_Image_Turbo_Xiang_Lora
Xiang Tease Grid Image
Prince_Xiang_white_brief_Z_Image_Turbo_tease_4_bind_images
Use lora from https://huggingface.co/svjack/Prince_Xiang_Z_Image_Turbo_Lora
Xiang Tease Grid Image
Xiang_Z_Image_Turbo_HairCut_ZH_Captioned
sdxl-turbo-fp-baselineTurbo-AI-TestingPrince_Xiang_Z_Image_Turbo_tease_4_bind_images
Use lora from https://huggingface.co/svjack/Prince_Xiang_Z_Image_Turbo_Lora
Xiang Tease Grid Image
turboquant-art-5kturboquant-art-1kdataset-sopravvivenzaturboquant-art-50k
