Instructions to use f5aiteam/ComfyUI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use f5aiteam/ComfyUI with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="f5aiteam/ComfyUI",
	filename="SEEDVR2/seedvr2_ema_3b-Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use f5aiteam/ComfyUI 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 f5aiteam/ComfyUI:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf f5aiteam/ComfyUI:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf f5aiteam/ComfyUI:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf f5aiteam/ComfyUI:UD-Q4_K_XL

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 f5aiteam/ComfyUI:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf f5aiteam/ComfyUI:UD-Q4_K_XL

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 f5aiteam/ComfyUI:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf f5aiteam/ComfyUI:UD-Q4_K_XL

Use Docker

docker model run hf.co/f5aiteam/ComfyUI:UD-Q4_K_XL

LM Studio
Jan
Ollama
How to use f5aiteam/ComfyUI with Ollama:
```
ollama run hf.co/f5aiteam/ComfyUI:UD-Q4_K_XL
```

Unsloth Studio

How to use f5aiteam/ComfyUI 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 f5aiteam/ComfyUI 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 f5aiteam/ComfyUI to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for f5aiteam/ComfyUI to start chatting

Atomic Chat new
Docker Model Runner
How to use f5aiteam/ComfyUI with Docker Model Runner:
```
docker model run hf.co/f5aiteam/ComfyUI:UD-Q4_K_XL
```

Lemonade

How to use f5aiteam/ComfyUI with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull f5aiteam/ComfyUI:UD-Q4_K_XL

Run and chat with the model

lemonade run user.ComfyUI-UD-Q4_K_XL

List all available models

lemonade list

f5aiteam commited on Dec 2, 2025

Commit

492bc8c

verified ·

1 Parent(s): c28e630

Upload 9 files

Browse files

F:\stable-diffusion-webui\models\diffusion_models\Flux

Files changed (10) hide show

.gitattributes +4 -0
diffusion_models/Flux/Flux1-Dev-SRPO-v1-fp8.safetensors +3 -0
diffusion_models/Flux/flux1-dev-Q6_K.gguf +3 -0
diffusion_models/Flux/flux1-dev-bnb-nf4-v2.safetensors +3 -0
diffusion_models/Flux/flux1-dev-fp8-e4m3fn.safetensors +3 -0
diffusion_models/Flux/flux1-dev-kontext_fp8_scaled.safetensors +3 -0
diffusion_models/Flux/flux1-fill-dev-Q8_0.gguf +3 -0
diffusion_models/Flux/flux1-kontext-dev-Q8_0.gguf +3 -0
diffusion_models/Flux/fluxSigmaVision_fp8.safetensors +3 -0
diffusion_models/Flux/fluxSigmaVision_q4KS.gguf +3 -0

@@ -38,3 +38,7 @@ clip/Qwen2.5-VL-7B-Instruct-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
 clip/t5-v1_1-xxl-encoder-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 clip/t5-v1_1-xxl-encoder-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
 clip/t5-v1_1-xxl-encoder-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

 clip/t5-v1_1-xxl-encoder-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 clip/t5-v1_1-xxl-encoder-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
 clip/t5-v1_1-xxl-encoder-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+diffusion_models/Flux/flux1-dev-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+diffusion_models/Flux/flux1-fill-dev-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+diffusion_models/Flux/flux1-kontext-dev-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+diffusion_models/Flux/fluxSigmaVision_q4KS.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:388f985c617a5f5d799a936a71d3836fafaa2224702c085a58e9e081a57cf95d
+size 11901562654

+version https://git-lfs.github.com/spec/v1
+oid sha256:9566d56031d7f8de184bb5a0393073956ec4e28b32db3f860bd2b87edca04d13
+size 9857000736

+version https://git-lfs.github.com/spec/v1
+oid sha256:fef37763b8f2c8cc3463139bbb6d91aa517c605b654d4e5c540de52813f30306
+size 12044280207

+version https://git-lfs.github.com/spec/v1
+oid sha256:47d8dbdc6da6e996ff31567476c0a549afd1a99554b20af2be57f0ccfa93aa36
+size 11901525888

+version https://git-lfs.github.com/spec/v1
+oid sha256:630ba795ec64283b4230ea23cf79406c2c68b7c578229ed139f30043eadb30a2
+size 11904640136

+version https://git-lfs.github.com/spec/v1
+oid sha256:345ffd7acf39148e391133ae2a2fa7cc3f85e8dd0dbdb4636e760c3e7fe7952d
+size 12727035168

+version https://git-lfs.github.com/spec/v1
+oid sha256:ff2ff71c3755c8ab394398a412252c23382a83138b65190b16e736d457b80f73
+size 12714452256

+version https://git-lfs.github.com/spec/v1
+oid sha256:6d751b0b3dfe569bebca309df455a85b24db36b1b5d9604a82b0d3a8c96c362c
+size 11891266952

+version https://git-lfs.github.com/spec/v1
+oid sha256:889ad61cac917de64693561d0cd767fd04bcc2245868a1a2f26d2706f2fbd73f
+size 6777785248

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@