SD3.5 Large (13.5GB) Improved Triple CLIP -- Full Checkpoint --

LARGE_3CLIP_FLAN-FP16
Felldude
11 months ago

SD3.5 Large (13.5GB) Improved Triple CLIP

This is not a waifu generator (YET)

  • Large Model SD 3.5 Base

  • UNET is not modified other then to quantize to FP8 (To fit into 16GB VRAM)

  • BF16 T5xxl (From FP32), Custom CLIP-G and Improved CLIP-L (Quantized)

  • Triple CLIP

Works in Comfy-UI without any modification just load checkpoint and go.

My IT's per Second on an old 3050 8GB RTX

SD 3.5 Medium (Dual CLIP Hybrid)

8GB - Not tested

11GB - 1IT per second

SD 3.5 Large (Triple CLIP FP8)

13.5GB - 8 Seconds Per IT

26GB (FP16 FULL) - 30 Seconds per IT

Read more...

What is SD3.5 Large (13.5GB) Improved Triple CLIP -- Full Checkpoint --?

SD3.5 Large (13.5GB) Improved Triple CLIP -- Full Checkpoint -- is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user Felldude. Derived from the powerful Stable Diffusion (SD 3.5) model, SD3.5 Large (13.5GB) Improved Triple CLIP -- Full Checkpoint -- has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that SD3.5 Large (13.5GB) Improved Triple CLIP -- Full Checkpoint -- is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as base model, checkpoint, fp8.

With a rating of 0 and over 0 ratings, SD3.5 Large (13.5GB) Improved Triple CLIP -- Full Checkpoint -- is a popular choice among users for generating high-quality images from text prompts.

Can I download SD3.5 Large (13.5GB) Improved Triple CLIP -- Full Checkpoint --?

Yes! You can download the latest version of SD3.5 Large (13.5GB) Improved Triple CLIP -- Full Checkpoint -- from here.

How to use SD3.5 Large (13.5GB) Improved Triple CLIP -- Full Checkpoint --?

To use SD3.5 Large (13.5GB) Improved Triple CLIP -- Full Checkpoint --, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like SD3.5 Large (13.5GB) Improved Triple CLIP -- Full Checkpoint --, check out our crash course in AI image generation.

Download (25.1 GB) Download available on desktop only
You'll need to use a program like A1111 to run this – learn how in our crash course

Popularity

80 ~10

Info

Base model: SD 3.5

Latest version (LARGE_3CLIP_FLAN-FP16): 1 File

To download these files, please visit this page from a desktop computer.

5 Versions

😥 There are no SD3.5 Large (13.5GB) Improved Triple CLIP -- Full Checkpoint -- LARGE_3CLIP_FLAN-FP16 prompts yet!

Go ahead and upload yours!

No results

Your query returned no results – please try removing some filters or trying a different term.