Sign In

Long CLIP (Distilled)

Download

1 variant available

fp32 SafeTensor

Predict_CLIP.safetensors

Full precision, largest file (pruned) • 471.71 MB

Verified:

Type
Checkpoint Trained
Stats

403

Reviews
Published

Sep 6, 2025

Base Model

SDXL 1.0

Training
Steps: 600,000
Epochs: 10
Hash
AutoV2
285D9282C4
default creator card background decoration
Reactions - 65090

65.1K

Downloads - 605239

605.2K

Generations - 4937295

4.9M

SDXL Training Contest Participant
ComfyUI_00019_.png

Long CLIP (Distilled)

  • Teacher/Student Distillation from 248/218 token length to projected 77

  • Pruned for use in SDXL, FLUX, SD 1.5, SD3, Hunyaun Video

  • DO NOT USE IN HI-DREAM, PONY (In most cases), or iLLustrious

  • Some of the top onsite models built with FP32 Distilled CLIP/FP32 VAE

  • Forcing FP32 CLIP recommended for Comfy, Forge, Auto1111


HiDream CLIP has been trained on a distillation set and the 248 and 218 token lengths reduced to 77 based on the pooled vision/text model output.