Sign In
homemodelsimagesvideos3D Modelsarticlescomicsbountieschallengesupdatesshop

Long CLIP (Distilled)

Updated: Sep 6, 2025

base modelhidreamfp32sdxlfluxclip-l

Download

1 variant available

fp32 SafeTensor

LongCLIP_Distilled.safetensors

Full precision, largest file • 471.71 MB

Verified:

Type
Checkpoint Trained
Stats

1,567

Reviews

(89)

Published

Jul 24, 2025

Base Model

Flux.1 D

Training
Steps: 100,000
Epochs: 10
Hash
AutoV2
D7E621F1E0
default creator card background decoration
Reactions - 65090

65.1K

Downloads - 605448

605.4K

Generations - 4937965

4.9M

SDXL Training Contest Participant

License:

FLUX.1 [dev] Non-Commercial License

The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.

IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

ComfyUI_00018_.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.