---
license: apache-2.0
base_model:
- ByteDance-Seed/BAGEL-7B-MoT
pipeline_tag: any-to-any
widget:
- text: >-
    a female cosplayer portraying an ethereal fairy or elf, wearing a flowing
    dress made of delicate fabrics in soft, mystical colors like emerald green
    and silver. She has pointed ears, a gentle, enchanting expression, and her
    outfit is adorned with sparkling jewels and intricate patterns. The
    background is a magical forest with glowing plants, mystical creatures, and
    a serene atmosphere
  output:
    url: samples\image1.webp
- text: >-
    a female cosplayer portraying an ethereal fairy or elf, wearing a flowing
    dress made of delicate fabrics in soft, mystical colors like emerald green
    and silver. She has pointed ears, a gentle, enchanting expression, and her
    outfit is adorned with sparkling jewels and intricate patterns. The
    background is a magical forest with glowing plants, mystical creatures, and
    a serene atmosphere
  output:
    url: samples\image7.webp
- text: >-
    a female cosplayer portraying an ethereal fairy or elf, wearing a flowing
    dress made of delicate fabrics in soft, mystical colors like emerald green
    and silver. She has pointed ears, a gentle, enchanting expression, and her
    outfit is adorned with sparkling jewels and intricate patterns. The
    background is a magical forest with glowing plants, mystical creatures, and
    a serene atmosphere
  output:
    url: samples\image3.webp
- text: >-
    Original picture (part of prompt)
  output:
    url: samples\image4.webp
- text: >-
    She boards a modern subway, quietly reading a folded newspaper, wearing the same clothes.
  output:
    url: samples\image5.webp
- text: >-
    She boards a modern subway, quietly reading a folded newspaper, wearing the same clothes.
  parameters:
    negative_prompt: same prompt as the left one with the same demo picture
  output:
    url: samples\image6.webp
tags:
- gguf-connector
---
## gguf quantized and fp8/16 scaled version of bagel
- base model from [bytedance-seed](https://huggingface.co/ByteDance-Seed)
- multimodal trial model (i.e., t2i, image editing/recogition)

### **run it with gguf-connector**
```
ggc b2
```

![screenshot](https://raw.githubusercontent.com/calcuis/multimodal-trial-model/master/demo.png)

<Gallery />

![screenshot](https://raw.githubusercontent.com/calcuis/multimodal-trial-model/master/demo2.png)

### **review/reference**
- simply execute the command (`ggc b2`) above in console/terminal
- opt a `vae` then opt a `model` file in the current directory to interact (see example below)

>
>Detecting GGUF/Safetensors...
>
>GGUF file(s) available. Select which one for VAE:
>1. pig_ae_fp32-f16.gguf
>2. pig_ae_fp32-f32.gguf
>
>Enter your choice (1 to 2): 1
>
>VAE file: pig_ae_fp32-f16.gguf is selected!
>
>
>Safetensors file(s) available. Select which one for MODEL:
>1. ema_bf16.safetensors
>2. ema_fp16.safetensors (for non-cuda user)
>3. ema_fp8_e4m3fn.safetensors (recommended)
>4. ema_fp8_e5m2.safetensors
>
>Enter your choice (1 to 4): _
>

- note: for the latest update, only tokenizer will be pulled to gguf-connector folder (cache) automatically during the first launch; you need to prepare the bulky model and vae files still, working like [vision](https://huggingface.co/calcuis/llava-gguf) connector right away; mix and match, more flexible
- run it entirely offline; i.e., from local URL:  http://127.0.0.1:7860 with lazy webui
- require dependency: bagel2; `pip install bagel2`; for flash-attn and triton, could opt to install it with pre-built wheels, i.e.,[here](https://github.com/calcuis/multimodal-trial-model/releases), unless you can build the wheel yourself successfully
- might need some optional dependencies, please refer to the [checklist](https://github.com/calcuis/multimodal-trial-model/blob/main/requirements.txt); as connector won't force your machine to install any of those by default
- gguf-connector ([pypi](https://pypi.org/project/gguf-connector))