Downloads · 30 days
864
21% of all-time downloads
QuantFactory/TIPO-500M-GGUF
TIPO-500M-GGUF is a text generation model from QuantFactory. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
Downloads · 30 days
864
21% of all-time downloads
All-time downloads
4.1K
Public
Repo size
4.6 GB
Likes
4
Public
Click a slice to open those files.
.gguf4.6 GB · 100%
From the Hugging Face model README
This is quantized version of KBlueLeaf/TIPO-500M created using llama.cpp
500M LLaMA arch model trained for TIPO.<br> Tech Report: https://hackmd.io/@KBlueLeaf/BJULOQBR0

In this project, we introduce "TIPO" (Text to Image with text presampling for Prompt Optimization), an innovative framework designed to significantly enhance the quality and usability of Text-to-Image (T2I) generative models. TIPO utilizes the Large Language Models (LLMs) to perform "Text Presampling" within the inference pipeline of text-to-image generative modeling. By refining and extending user input prompts, TIPO enables generative models to produce superior results with minimal user effort, making T2I systems more accessible and effective for a wider range of users.
Use updated version of DTG extension (renamed to z-tipo-extension), current version of z-tipo-extension support stable-diffusion-webui, stable-diffusion-webui-forge and ComfyUI. SD-Next haven't been tested. https://github.com/KohakuBlueleaf/z-tipo-extension
This model is LLaMA arch with 500M parameters, the training data is combined version of Danbooru2023, GBC10M and Coyo-HD-11M.<br> The total token seen is around 30B tokens.<br> For more information please refer to the tech report and following table.
| TIPO-200M | TIPO-500M | |
|---|---|---|
| Arch | LLaMA | LLaMA |
| Max ctx length | 1024 | 1024 |
| Batch Size | 2048 | 3584 |
| Training dataset | Danbooru, GBC10M, 5epoch<br />Danbooru, GBC10M, Coyo11M, 3epoch | Danbooru, GBC10M, Coyo11M, 5epoch |
| Real Token Seen* | 40B token | 30B token |
| Training Hardware | RTX 3090 x 4 | H100 x 8 |
| Training Time | 420 hour` | 100 hour` |
| URL | KBlueLeaf/TIPO-200M · Hugging Face | KBlueLeaf/TIPO-500M · Hugging Face |
*: We only count "non-padding token" in the token seen, since all the training data have very large length range <br/> `: Since the training data is pretty short, it cost more time to reach same token seen than general LLM pretraining.<br/> As reference, with 4096 as max ctx length and almost all the data have reach that length, you may only need 2days to reach 10B token seen on RTX 3090 x 4 with 200M model.
We have tested TIPO in several metric:
We compute the Aesthetic Score using the Aesthetic Predictor V2.5. This metric is calculated on the short/truncated long test.

Figure 1: Aesthetic Score distribution.
The AI Corrupt Score is obtained from the AICorruptMetrics in sdeval.
This metric is calculated on the short/truncated long test.

Figure 2: AI Corrupt Score distribution.
We use FDD on the Scenery Tag Test to demonstrate that when input prompts address a smaller distribution, the model struggles to generate images that reflect the true distribution. However, with TIPO, this issue is mitigated.
| FDD Model | <meta> scenery only | <meta> scenery + TIPO |
|---|---|---|
| DinoV2 ViT-S | 0.1917 | 0.1786 |
| DinoV2 ViT-B | 0.2002 | 0.1755 |
| DinoV2 ViT-L | 0.2017 | 0.1863 |
| DinoV2 ViT-G | 0.2359 | 0.2096 |
Table 1: Frechet Dino Distance (FDD) on Scenery Tag Test.
This model is released under Kohaku License 1.0<br> You can check the above provided URL or check the LICENSE file in this repo.
@misc{yeh2024tipo,
title = {TIPO: Text to Image with text presampling for Prompt Optimization},
author = {Yeh, Shih-Ying},
year = {2024},
month = {9},
day = {29},
note = {Technical report available at \url{https://hackmd.io/@KBlueLeaf/BJULOQBR0}.
Model available at \url{https://huggingface.co/KBlueLeaf/TIPO-500M}.
Source code available at \url{https://github.com/KohakuBlueleaf/KGen}},
}