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

Libraries

How to use StableDiffusionVN/Flux with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="StableDiffusionVN/Flux",
	filename="Clip/t5-v1_1-xxl-encoder-Q4_K_S.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use StableDiffusionVN/Flux with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf StableDiffusionVN/Flux:Q4_K_S
# Run inference directly in the terminal:
llama-cli -hf StableDiffusionVN/Flux:Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf StableDiffusionVN/Flux:Q4_K_S
# Run inference directly in the terminal:
llama-cli -hf StableDiffusionVN/Flux:Q4_K_S

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 StableDiffusionVN/Flux:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf StableDiffusionVN/Flux:Q4_K_S

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 StableDiffusionVN/Flux:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf StableDiffusionVN/Flux:Q4_K_S

Use Docker

docker model run hf.co/StableDiffusionVN/Flux:Q4_K_S

LM Studio
Jan
Ollama
How to use StableDiffusionVN/Flux with Ollama:
```
ollama run hf.co/StableDiffusionVN/Flux:Q4_K_S
```

Unsloth Studio new

How to use StableDiffusionVN/Flux 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 StableDiffusionVN/Flux 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 StableDiffusionVN/Flux to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use StableDiffusionVN/Flux with Docker Model Runner:
```
docker model run hf.co/StableDiffusionVN/Flux:Q4_K_S
```

Lemonade

How to use StableDiffusionVN/Flux with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull StableDiffusionVN/Flux:Q4_K_S

Run and chat with the model

lemonade run user.Flux-Q4_K_S

List all available models

lemonade list

Flux / ComfyUI_workflow /Flux_schnell_text-img.json

phamhungd

Upload 2 files

ffbc42b verified almost 2 years ago

raw

history blame contribute delete

6.58 kB

	{
	"last_node_id": 69,
	"last_link_id": 114,
	"nodes": [
	{
	"id": 8,
	"type": "VAEDecode",
	"pos": [
	1178,
	91
	],
	"size": {
	"0": 210,
	"1": 46
	},
	"flags": {},
	"order": 5,
	"mode": 0,
	"inputs": [
	{
	"name": "samples",
	"type": "LATENT",
	"link": 66
	},
	{
	"name": "vae",
	"type": "VAE",
	"link": 88
	}
	],
	"outputs": [
	{
	"name": "IMAGE",
	"type": "IMAGE",
	"links": [
	9
	],
	"slot_index": 0
	}
	],
	"properties": {
	"Node name for S&R": "VAEDecode"
	}
	},
	{
	"id": 9,
	"type": "SaveImage",
	"pos": [
	1422,
	88
	],
	"size": {
	"0": 356.08502197265625,
	"1": 499.8143310546875
	},
	"flags": {},
	"order": 6,
	"mode": 0,
	"inputs": [
	{
	"name": "images",
	"type": "IMAGE",
	"link": 9
	}
	],
	"properties": {
	"Node name for S&R": "SaveImage"
	},
	"widgets_values": [
	"ComfyUI"
	]
	},
	{
	"id": 69,
	"type": "CLIPTextEncode",
	"pos": [
	408,
	89
	],
	"size": {
	"0": 400,
	"1": 200
	},
	"flags": {},
	"order": 3,
	"mode": 0,
	"inputs": [
	{
	"name": "clip",
	"type": "CLIP",
	"link": 111
	}
	],
	"outputs": [
	{
	"name": "CONDITIONING",
	"type": "CONDITIONING",
	"links": [
	112,
	114
	],
	"shape": 3
	}
	],
	"properties": {
	"Node name for S&R": "CLIPTextEncode"
	},
	"widgets_values": [
	"Actual image of a smiling Vietnamese girl. With both hands she was holding a notice board with the word \"FluxAI by SDVN.ME\" large in the middle. Photos have high detail"
	]
	},
	{
	"id": 53,
	"type": "EmptyLatentImage",
	"pos": [
	499,
	347
	],
	"size": {
	"0": 303.3410339355469,
	"1": 111.14437103271484
	},
	"flags": {},
	"order": 0,
	"mode": 0,
	"outputs": [
	{
	"name": "LATENT",
	"type": "LATENT",
	"links": [
	85
	],
	"shape": 3
	}
	],
	"properties": {
	"Node name for S&R": "EmptyLatentImage"
	},
	"widgets_values": [
	512,
	512,
	1
	]
	},
	{
	"id": 68,
	"type": "Note",
	"pos": [
	65,
	237
	],
	"size": {
	"0": 312.59844970703125,
	"1": 99.95023345947266
	},
	"flags": {},
	"order": 1,
	"mode": 0,
	"properties": {
	"text": ""
	},
	"widgets_values": [
	"ComfyUI Colab:\n- Creator: stablediffusion.vn\n- Website: sdvn.me \| comfy.vn \| fluxai.vn\n- Document: bit.ly/sdvn-lib\n- Skills training: hungdiffusion.com"
	],
	"color": "#432",
	"bgcolor": "#653"
	},
	{
	"id": 52,
	"type": "CheckpointLoaderSimple",
	"pos": [
	63,
	89
	],
	"size": {
	"0": 315,
	"1": 98
	},
	"flags": {},
	"order": 2,
	"mode": 0,
	"outputs": [
	{
	"name": "MODEL",
	"type": "MODEL",
	"links": [
	89
	],
	"shape": 3,
	"slot_index": 0
	},
	{
	"name": "CLIP",
	"type": "CLIP",
	"links": [
	111
	],
	"shape": 3,
	"slot_index": 1
	},
	{
	"name": "VAE",
	"type": "VAE",
	"links": [
	88
	],
	"shape": 3,
	"slot_index": 2
	}
	],
	"properties": {
	"Node name for S&R": "CheckpointLoaderSimple"
	},
	"widgets_values": [
	"Flux_schnell_v1-fp8.safetensors"
	]
	},
	{
	"id": 44,
	"type": "KSampler",
	"pos": [
	837,
	93
	],
	"size": {
	"0": 318.3961181640625,
	"1": 487.5167236328125
	},
	"flags": {},
	"order": 4,
	"mode": 0,
	"inputs": [
	{
	"name": "model",
	"type": "MODEL",
	"link": 89
	},
	{
	"name": "positive",
	"type": "CONDITIONING",
	"link": 112
	},
	{
	"name": "negative",
	"type": "CONDITIONING",
	"link": 114
	},
	{
	"name": "latent_image",
	"type": "LATENT",
	"link": 85,
	"slot_index": 3
	}
	],
	"outputs": [
	{
	"name": "LATENT",
	"type": "LATENT",
	"links": [
	66
	],
	"shape": 3,
	"slot_index": 0
	}
	],
	"properties": {
	"Node name for S&R": "KSampler"
	},
	"widgets_values": [
	1,
	"fixed",
	4,
	1,
	"euler",
	"simple",
	1
	]
	}
	],
	"links": [
	[
	9,
	8,
	0,
	9,
	0,
	"IMAGE"
	],
	[
	66,
	44,
	0,
	8,
	0,
	"LATENT"
	],
	[
	75,
	10,
	0,
	8,
	1,
	"VAE"
	],
	[
	76,
	12,
	0,
	44,
	0,
	"MODEL"
	],
	[
	77,
	11,
	0,
	48,
	0,
	"CLIP"
	],
	[
	78,
	10,
	0,
	30,
	1,
	"VAE"
	],
	[
	79,
	12,
	0,
	51,
	0,
	"MODEL"
	],
	[
	80,
	11,
	0,
	51,
	1,
	"CLIP"
	],
	[
	81,
	10,
	0,
	51,
	2,
	"VAE"
	],
	[
	85,
	53,
	0,
	44,
	3,
	"LATENT"
	],
	[
	88,
	52,
	2,
	8,
	1,
	"VAE"
	],
	[
	89,
	52,
	0,
	44,
	0,
	"MODEL"
	],
	[
	111,
	52,
	1,
	69,
	0,
	"CLIP"
	],
	[
	112,
	69,
	0,
	44,
	1,
	"CONDITIONING"
	],
	[
	114,
	69,
	0,
	44,
	2,
	"CONDITIONING"
	]
	],
	"groups": [],
	"config": {},
	"extra": {
	"ds": {
	"scale": 1.331000000000001,
	"offset": [
	-70.43711732987452,
	13.751635799046973
	]
	}
	},
	"version": 0.4
	}