Instructions to use for-comfyui/comfyui-data with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use for-comfyui/comfyui-data with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf for-comfyui/comfyui-data:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf for-comfyui/comfyui-data:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf for-comfyui/comfyui-data:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf for-comfyui/comfyui-data:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf for-comfyui/comfyui-data:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf for-comfyui/comfyui-data:Q4_K_M

Use Docker

docker model run hf.co/for-comfyui/comfyui-data:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use for-comfyui/comfyui-data with Ollama:
```
ollama run hf.co/for-comfyui/comfyui-data:Q4_K_M
```
Unsloth Desktop

How to use for-comfyui/comfyui-data with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf for-comfyui/comfyui-data:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "for-comfyui/comfyui-data:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use for-comfyui/comfyui-data with Docker Model Runner:
```
docker model run hf.co/for-comfyui/comfyui-data:Q4_K_M
```

Lemonade

How to use for-comfyui/comfyui-data with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull for-comfyui/comfyui-data:Q4_K_M

Run and chat with the model

lemonade run user.comfyui-data-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use for-comfyui/comfyui-data with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf for-comfyui/comfyui-data:Q4_K_M

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 for-comfyui/comfyui-data:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use for-comfyui/comfyui-data with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf for-comfyui/comfyui-data:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "for-comfyui/comfyui-data:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

yizhoucp commited on Oct 10

Commit

750c52c

verified ·

1 Parent(s): 8004fca

Publish h3 runtime assets

Browse files

Files changed (6) hide show

custom_nodes_image2Video_h3.tar.gz +2 -2
models_image2Video_h3/LLM/gemma-4-12B-it-heretic-QAT-UD-Q4_K_XL.gguf +0 -3
models_image2Video_h3/LLM/mmproj-BF16.gguf +0 -3
models_image2Video_h3/LLM/prompts/H3_NSFW_Physics_Engine.txt +0 -1
requirements_image2Video_h3.lock +0 -7
workflows_image2Video_h3.tar.gz +2 -2

custom_nodes_image2Video_h3.tar.gz CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cc1e51dcd4ab8caf848d0878a85528d138528073c20a971524c737a405400b5
-size 8510219

 version https://git-lfs.github.com/spec/v1
+oid sha256:96fe97848888b8ce8cf2b3b518e6cbac32bbd529b753661b741651d0dcca7d69
+size 8507862

models_image2Video_h3/LLM/gemma-4-12B-it-heretic-QAT-UD-Q4_K_XL.gguf DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d66f8198cf21219c93ebc682919398a151f67cd81ca54c9e6b125b34446b16e4
-size 6716355776

models_image2Video_h3/LLM/mmproj-BF16.gguf DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dcb8103adad042b1bf99df767aaf34eb37c5a73a4a2f0417e4d7ba557e91664f
-size 175115840

models_image2Video_h3/LLM/prompts/H3_NSFW_Physics_Engine.txt DELETED Viewed

	@@ -1 +0,0 @@
1	- You are a MiniMax H3 visual and physics prompt expander. Preserve identity, clothing, lighting, and scene facts. Do not invent unseen details.

requirements_image2Video_h3.lock CHANGED Viewed

@@ -57,10 +57,6 @@ botocore==1.42.86 \
     --hash=sha256:443387337864e069f7e4e885ccdc81592725b5598ca966514af3e9776bce0bfe \
     --hash=sha256:baa49e93b4c92d63e0c8288026ee1ef8de83f182743127cc9175504440a48e49
     # via -r requirements.in
-click==8.1.8 \
-    --hash=sha256:63c132bbbed01578a06712a2d1f497bb62d9c1c0d329b7903a866228027263b2 \
-    --hash=sha256:ed53c9d8990d83c2a27deae68e4ee337473f6330c040a31d4225c9574d16096a
-    # via -r requirements.in
 clip-interrogator==0.6.0 \
     --hash=sha256:cd7c6bf9db170f005b4179e943fc1658aa0f8eebcc75ab3428b0a992aaeabd1c \
     --hash=sha256:e7942372fe9b96181881f7083e3179de746e59b0e3c4199fb3e3e19bef421693
@@ -669,9 +665,6 @@ librosa==0.11.0 \
     --hash=sha256:0b6415c4fd68bff4c29288abe67c6d80b587e0e1e2cfb0aad23e4559504a7fa1 \
     --hash=sha256:f5ed951ca189b375bbe2e33b2abd7e040ceeee302b9bbaeeffdfddb8d0ace908
     # via -r requirements.in
-llama-cpp-python==0.3.35 \
-    --hash=sha256:1139dbb54509074b70893fab8554e3b079aa9f4d312058ce4018ef0019e3de12
-    # via -r requirements.in
 llvmlite==0.47.0 \
     --hash=sha256:003bcf7fa579e14db59c1a1e113f93ab8a06b56a4be31c7f08264d1d4072d077 \
     --hash=sha256:12a69d4bb05f402f30477e21eeabe81911e7c251cecb192bed82cd83c9db10d8 \

     --hash=sha256:443387337864e069f7e4e885ccdc81592725b5598ca966514af3e9776bce0bfe \
     --hash=sha256:baa49e93b4c92d63e0c8288026ee1ef8de83f182743127cc9175504440a48e49
     # via -r requirements.in
 clip-interrogator==0.6.0 \
     --hash=sha256:cd7c6bf9db170f005b4179e943fc1658aa0f8eebcc75ab3428b0a992aaeabd1c \
     --hash=sha256:e7942372fe9b96181881f7083e3179de746e59b0e3c4199fb3e3e19bef421693
     --hash=sha256:0b6415c4fd68bff4c29288abe67c6d80b587e0e1e2cfb0aad23e4559504a7fa1 \
     --hash=sha256:f5ed951ca189b375bbe2e33b2abd7e040ceeee302b9bbaeeffdfddb8d0ace908
     # via -r requirements.in
 llvmlite==0.47.0 \
     --hash=sha256:003bcf7fa579e14db59c1a1e113f93ab8a06b56a4be31c7f08264d1d4072d077 \
     --hash=sha256:12a69d4bb05f402f30477e21eeabe81911e7c251cecb192bed82cd83c9db10d8 \

workflows_image2Video_h3.tar.gz CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d62f6f586c422c0d9e7edb682be4b97651244077e2740ef9966f7e1caa6a724
-size 31269

 version https://git-lfs.github.com/spec/v1
+oid sha256:249b1c4678bea998684b76aef2c01ba2d1b8fa62a1a9acc70640e1ec70c84179
+size 26012