Instructions to use vantagewithai/Sulphur-2-Base-Split with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vantagewithai/Sulphur-2-Base-Split with Diffusers:

pip install -U diffusers transformers accelerate

import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image, export_to_video

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("vantagewithai/Sulphur-2-Base-Split", dtype=torch.bfloat16, device_map="cuda")
pipe.to("cuda")

prompt = "A man with short gray hair plays a red electric guitar."
image = load_image(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png"
)

output = pipe(image=image, prompt=prompt).frames[0]
export_to_video(output, "output.mp4")

llama-cpp-python

How to use vantagewithai/Sulphur-2-Base-Split with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="vantagewithai/Sulphur-2-Base-Split",
	filename="text_encoder/Qwen3.5-sulphur_prompt_enhancer-Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "{\n    \"image\": \"cat.png\",\n    \"prompt\": \"The cat starts to dance\"\n}"
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use vantagewithai/Sulphur-2-Base-Split with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vantagewithai/Sulphur-2-Base-Split:Q8_0
# Run inference directly in the terminal:
llama-cli -hf vantagewithai/Sulphur-2-Base-Split:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf vantagewithai/Sulphur-2-Base-Split:Q8_0
# Run inference directly in the terminal:
llama-cli -hf vantagewithai/Sulphur-2-Base-Split:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf vantagewithai/Sulphur-2-Base-Split:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf vantagewithai/Sulphur-2-Base-Split:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf vantagewithai/Sulphur-2-Base-Split:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vantagewithai/Sulphur-2-Base-Split:Q8_0

Use Docker

docker model run hf.co/vantagewithai/Sulphur-2-Base-Split:Q8_0

LM Studio
Jan
Ollama
How to use vantagewithai/Sulphur-2-Base-Split with Ollama:
```
ollama run hf.co/vantagewithai/Sulphur-2-Base-Split:Q8_0
```

Unsloth Studio new

How to use vantagewithai/Sulphur-2-Base-Split with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for vantagewithai/Sulphur-2-Base-Split to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for vantagewithai/Sulphur-2-Base-Split to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vantagewithai/Sulphur-2-Base-Split to start chatting

Pi new

How to use vantagewithai/Sulphur-2-Base-Split with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf vantagewithai/Sulphur-2-Base-Split:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "vantagewithai/Sulphur-2-Base-Split:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use vantagewithai/Sulphur-2-Base-Split with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf vantagewithai/Sulphur-2-Base-Split:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default vantagewithai/Sulphur-2-Base-Split:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use vantagewithai/Sulphur-2-Base-Split with Docker Model Runner:
```
docker model run hf.co/vantagewithai/Sulphur-2-Base-Split:Q8_0
```

Lemonade

How to use vantagewithai/Sulphur-2-Base-Split with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vantagewithai/Sulphur-2-Base-Split:Q8_0

Run and chat with the model

lemonade run user.Sulphur-2-Base-Split-Q8_0

List all available models

lemonade list

vantagewithai commited on 17 days ago

Commit

6145fcb

verified ·

1 Parent(s): 1bf2d74

Upload Vantage-Sulphur-2-Workflow.json

Browse files

Files changed (1) hide show

Vantage-Sulphur-2-Workflow.json +30 -31

Vantage-Sulphur-2-Workflow.json CHANGED Viewed

@@ -3557,7 +3557,6 @@
           "link": null
         },
         {
-          "dir": 3,
           "name": "any_05",
           "type": "LATENT",
           "link": null
@@ -4119,30 +4118,6 @@
       "color": "#232",
       "bgcolor": "#353"
     },
-    {
-      "id": 254,
-      "type": "MarkdownNote",
-      "pos": [
-        -962.6302735981759,
-        4950.248487143484
-      ],
-      "size": [
-        544.2015688405178,
-        727.2742475515188
-      ],
-      "flags": {},
-      "order": 23,
-      "mode": 0,
-      "inputs": [],
-      "outputs": [],
-      "title": "Model Links",
-      "properties": {},
-      "widgets_values": [
-        "## Model links\n\n**Sulphur-2 Models**\n\n- **BF16**: [sulphur_dev_bf16_model.safetensors](https://huggingface.co/vantagewithai/Sulphur-2-Base-Split/resolve/main/model/sulphur_dev_bf16_model.safetensors?download=true)\n- **FP8**: [sulphur_dev_model_fp8mixed.safetensors](https://huggingface.co/vantagewithai/Sulphur-2-Base-Split/resolve/main/model/sulphur_dev_model_fp8mixed.safetensors?download=true)\n- **GGUF**: [sulphur_dev-XX_X.gguf](https://huggingface.co/vantagewithai/Sulphur-2-Base-GGUF/tree/main)\n\n**text_encoders**\n\n- [gemma_3_12B_it.safetensors](https://huggingface.co/Comfy-Org/ltx-2/resolve/main/split_files/text_encoders/gemma_3_12B_it.safetensors)\n- [ltx-2-3-22b-text_encoder.safetensors](https://huggingface.co/vantagewithai/LTX-2.3-Split/resolve/main/text_encoder/ltx-2-3-22b-text_encoder.safetensors?download=true)\n\n**vae**\n\n- [ltx-2-3-22b-VAE.safetensors](https://huggingface.co/vantagewithai/LTX-2.3-Split/resolve/main/vae/ltx-2-3-22b-VAE.safetensors?download=true)\n- [ltx-2-3-22b-audio_vae.safetensors](https://huggingface.co/vantagewithai/LTX-2.3-Split/resolve/main/audio_vae/ltx-2-3-22b-audio_vae.safetensors?download=true)\n\n**loras**\n\n- [ltx-2.3-22b-distilled-lora-1.1_fro90_ceil72_condsafe.safetensors](https://huggingface.co/vantagewithai/Sulphur-2-Base-Split/resolve/main/lora/ltx-2.3-22b-distilled-lora-1.1_fro90_ceil72_condsafe.safetensors?download=true)\n\n**latent_upscale_models**\n\n- [ltx-2.3-spatial-upscaler-x2-1.1.safetensors](https://huggingface.co/Lightricks/LTX-2.3/resolve/main/ltx-2.3-spatial-upscaler-x2-1.1.safetensors?download=true)\n\n**Vocals Extraction**\n\n- [MelBandRoformer_fp32.safetensors](https://huggingface.co/Kijai/MelBandRoFormer_comfy/resolve/main/MelBandRoformer_fp32.safetensors?download=true)\n\nModel Storage Location\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│   ├── 📂 diffusion_models/\n│   │      └── sulphur_dev_bf16_model.safetensors\n│   │      └── MelBandRoformer_fp32.safetensors\n│   ├── 📂 unet/\n│   │      ├── sulphur_dev-XX_X.gguf\n│   ├── 📂 text_encoders/\n│   │      ├── gemma_3_12B_it.safetensors\n│   │      └── ltx-2-3-22b-text_encoder.safetensors\n│   ├── 📂 vae/\n│   │      ├── ltx-2-3-22b-VAE.safetensors\n│   │      └── ltx-2-3-22b-audio_vae.safetensors\n│   ├── 📂 loras/\n│   │      └── ltx-2.3-22b-distilled-lora-1.1_fro90_ceil72_condsafe.safetensors\n│   └── 📂 latent_upscale_models/\n│          └── ltx-2.3-spatial-upscaler-x2-1.1.safetensors\n```\n"
-      ],
-      "color": "#222",
-      "bgcolor": "#000"
-    },
     {
       "id": 393,
       "type": "PrimitiveStringMultiline",
@@ -4155,7 +4130,7 @@
         228.32081230701533
       ],
       "flags": {},
-      "order": 24,
       "mode": 0,
       "inputs": [],
       "outputs": [
@@ -4192,7 +4167,7 @@
         58
       ],
       "flags": {},
-      "order": 25,
       "mode": 0,
       "inputs": [],
       "outputs": [
@@ -4230,7 +4205,7 @@
       "flags": {
         "collapsed": false
       },
-      "order": 26,
       "mode": 0,
       "inputs": [],
       "outputs": [
@@ -4270,7 +4245,7 @@
         154
       ],
       "flags": {},
-      "order": 27,
       "mode": 0,
       "inputs": [],
       "outputs": [
@@ -4292,6 +4267,30 @@
       },
       "color": "#323",
       "bgcolor": "#535"
     }
   ],
   "links": [
@@ -5411,8 +5410,8 @@
     "ds": {
       "scale": 1.5000000000000022,
       "offset": [
-        446.6834084206685,
-        -4857.752099904979
       ]
     },
     "frontendVersion": "1.43.17",

           "link": null
         },
         {
           "name": "any_05",
           "type": "LATENT",
           "link": null
       "color": "#232",
       "bgcolor": "#353"
     },
     {
       "id": 393,
       "type": "PrimitiveStringMultiline",
         228.32081230701533
       ],
       "flags": {},
+      "order": 23,
       "mode": 0,
       "inputs": [],
       "outputs": [
         58
       ],
       "flags": {},
+      "order": 24,
       "mode": 0,
       "inputs": [],
       "outputs": [
       "flags": {
         "collapsed": false
       },
+      "order": 25,
       "mode": 0,
       "inputs": [],
       "outputs": [
         154
       ],
       "flags": {},
+      "order": 26,
       "mode": 0,
       "inputs": [],
       "outputs": [
       },
       "color": "#323",
       "bgcolor": "#535"
+    },
+    {
+      "id": 254,
+      "type": "MarkdownNote",
+      "pos": [
+        -962.6302735981759,
+        4950.248487143484
+      ],
+      "size": [
+        544.2015688405178,
+        727.2742475515188
+      ],
+      "flags": {},
+      "order": 27,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [],
+      "title": "Model Links",
+      "properties": {},
+      "widgets_values": [
+        "## Model links\n\n**Sulphur-2 Models**\n\n- **BF16**: [sulphur_dev_bf16_model.safetensors](https://huggingface.co/vantagewithai/Sulphur-2-Base-Split/resolve/main/model/sulphur_dev_bf16_model.safetensors?download=true)\n- **FP8**: [sulphur_dev_model_fp8mixed.safetensors](https://huggingface.co/vantagewithai/Sulphur-2-Base-Split/resolve/main/model/sulphur_dev_model_fp8mixed.safetensors?download=true)\n- **GGUF**: [sulphur_dev-XX_X.gguf](https://huggingface.co/vantagewithai/Sulphur-2-Base-GGUF/tree/main)\n\n**text_encoders**\n\n- [gemma_3_12B_it.safetensors](https://huggingface.co/Comfy-Org/ltx-2/resolve/main/split_files/text_encoders/gemma_3_12B_it.safetensors)\n- [ltx-2-3-22b-text_encoder.safetensors](https://huggingface.co/vantagewithai/LTX-2.3-Split/resolve/main/text_encoder/ltx-2-3-22b-text_encoder.safetensors?download=true)\n\n**vae**\n\n- [ltx-2-3-22b-VAE.safetensors](https://huggingface.co/vantagewithai/LTX-2.3-Split/resolve/main/vae/ltx-2-3-22b-VAE.safetensors?download=true)\n- [ltx-2-3-22b-audio_vae.safetensors](https://huggingface.co/vantagewithai/LTX-2.3-Split/resolve/main/audio_vae/ltx-2-3-22b-audio_vae.safetensors?download=true)\n\n**loras**\n\n- [ltx-2.3-22b-distilled-lora-1.1_fro90_ceil72_condsafe.safetensors](https://huggingface.co/vantagewithai/Sulphur-2-Base-Split/resolve/main/lora/ltx-2.3-22b-distilled-lora-1.1_fro90_ceil72_condsafe.safetensors?download=true)\n\n**latent_upscale_models**\n\n- [ltx-2.3-spatial-upscaler-x2-1.1.safetensors](https://huggingface.co/Lightricks/LTX-2.3/resolve/main/ltx-2.3-spatial-upscaler-x2-1.1.safetensors?download=true)\n\n**Vocals Extraction**\n\n- [MelBandRoformer_fp32.safetensors](https://huggingface.co/Kijai/MelBandRoFormer_comfy/resolve/main/MelBandRoformer_fp32.safetensors?download=true)\n\n**Prompt Enhancer**\n\n- [Qwen3.5-sulphur_prompt_enhancer-Q8_0.gguf](https://huggingface.co/vantagewithai/Sulphur-2-Base-Split/resolve/main/text_encoder/Qwen3.5-sulphur_prompt_enhancer-Q8_0.gguf?download=true)\n- [mmproj-BF16.gguf](https://huggingface.co/vantagewithai/Sulphur-2-Base-Split/resolve/main/text_encoder/mmproj-BF16.gguf?download=true)\n\nModel Storage Location\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│   ├── 📂 diffusion_models/\n│   │      └── sulphur_dev_bf16_model.safetensors\n│   │      └── MelBandRoformer_fp32.safetensors\n│   ├── 📂 unet/\n│   │      ├── sulphur_dev-XX_X.gguf\n│   ├── 📂 text_encoders/\n│   │      ├── gemma_3_12B_it.safetensors\n│   │      └── ltx-2-3-22b-text_encoder.safetensors\n│   │      └── Qwen3.5-sulphur_prompt_enhancer-Q8_0.gguf\n│   │      └── mmproj-BF16.gguf\n│   ├── 📂 vae/\n│   │      ├── ltx-2-3-22b-VAE.safetensors\n│   │      └── ltx-2-3-22b-audio_vae.safetensors\n│   ├── 📂 loras/\n│   │      └── ltx-2.3-22b-distilled-lora-1.1_fro90_ceil72_condsafe.safetensors\n│   └── 📂 latent_upscale_models/\n│          └── ltx-2.3-spatial-upscaler-x2-1.1.safetensors\n```\n"
+      ],
+      "color": "#222",
+      "bgcolor": "#000"
     }
   ],
   "links": [
     "ds": {
       "scale": 1.5000000000000022,
       "offset": [
+        446.6834084206686,
+        -4859.752099904979
       ]
     },
     "frontendVersion": "1.43.17",