Instructions to use aka7774/comfyui-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use aka7774/comfyui-models with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("aka7774/comfyui-models", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - llama-cpp-python
How to use aka7774/comfyui-models with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="aka7774/comfyui-models", filename="SEEDVR2/seedvr2_ema_7b-Q4_K_M.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use aka7774/comfyui-models 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 aka7774/comfyui-models:UD-Q4_K_XL # Run inference directly in the terminal: llama cli -hf aka7774/comfyui-models: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 aka7774/comfyui-models:UD-Q4_K_XL # Run inference directly in the terminal: llama cli -hf aka7774/comfyui-models: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 aka7774/comfyui-models:UD-Q4_K_XL # Run inference directly in the terminal: ./llama-cli -hf aka7774/comfyui-models: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 aka7774/comfyui-models:UD-Q4_K_XL # Run inference directly in the terminal: ./build/bin/llama-cli -hf aka7774/comfyui-models:UD-Q4_K_XL
Use Docker
docker model run hf.co/aka7774/comfyui-models:UD-Q4_K_XL
- LM Studio
- Jan
- Ollama
How to use aka7774/comfyui-models with Ollama:
ollama run hf.co/aka7774/comfyui-models:UD-Q4_K_XL
- Unsloth Studio
How to use aka7774/comfyui-models 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 aka7774/comfyui-models 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 aka7774/comfyui-models to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for aka7774/comfyui-models to start chatting
- Atomic Chat new
- Docker Model Runner
How to use aka7774/comfyui-models with Docker Model Runner:
docker model run hf.co/aka7774/comfyui-models:UD-Q4_K_XL
- Lemonade
How to use aka7774/comfyui-models with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull aka7774/comfyui-models:UD-Q4_K_XL
Run and chat with the model
lemonade run user.comfyui-models-UD-Q4_K_XL
List all available models
lemonade list
| { | |
| "model_type": "zonos2", | |
| "dtype": "bfloat16", | |
| "n_layers": 28, | |
| "dim": 2048, | |
| "head_dim": 128, | |
| "n_heads": null, | |
| "n_kv_heads": 4, | |
| "ffn_dim_multiplier": 1.5, | |
| "multiple_of": 256, | |
| "norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "max_seqlen": 6144, | |
| "n_codebooks": 9, | |
| "codebook_size": 1024, | |
| "eoa_id": 1024, | |
| "audio_pad_id": 1025, | |
| "text_vocab": 519, | |
| "loss_softcap": 15.0, | |
| "speaker_enabled": true, | |
| "speaker_embedding_dim": 2048, | |
| "speaker_lda_dim": 1024, | |
| "speaker_background_token_enabled": true, | |
| "accurate_mode_token_enabled": true, | |
| "speaking_rate_num_buckets": 8, | |
| "speaking_rate_buckets": ["0-8", "8-11", "11-14", "14-17", "17-21", "21-28", "28-40", "40+"], | |
| "quality_num_buckets": 60, | |
| "quality_features": [ | |
| "lufs", | |
| "estimated_snr", | |
| "max_pause", | |
| "estimated_bandlimit_hz", | |
| "leading_silence_s", | |
| "trailing_silence_s" | |
| ], | |
| "quality_buckets": { | |
| "lufs": ["-1000--50", "-50--45.5", "-45.5--41", "-41--36.5", "-36.5--32", "-32--27.5", "-27.5--23", "-23--18.5", "-18.5--14", "-14--9.5", "-9.5--5", "-5+"], | |
| "estimated_snr": ["-1000-0", "0-6", "6-12", "12-18", "18-24", "24-30", "30-36", "36-42", "42-48", "48-54", "54-60", "60+"], | |
| "max_pause": ["0-0.5", "0.5-1", "1-1.5", "1.5-2", "2-2.5", "2.5-3", "3-3.5", "3.5-4", "4-4.5", "4.5-5", "5-5.5", "5.5-6"], | |
| "estimated_bandlimit_hz": ["495.3-3433", "3433-6371", "6371-9310", "9310-12248", "12248-15186", "15186-18124", "18124-21062", "21062-24000"], | |
| "leading_silence_s": ["0-0.05", "0.05-0.1", "0.1-0.25", "0.25-0.5", "0.5-1", "1-2", "2-4", "4+"], | |
| "trailing_silence_s": ["0-0.05", "0.05-0.1", "0.1-0.25", "0.25-0.5", "0.5-1", "1-2", "2-4", "4+"] | |
| }, | |
| "quality_dropout": { | |
| "lufs": 0.25, | |
| "estimated_snr": 0.25, | |
| "max_pause": 0.25, | |
| "estimated_bandlimit_hz": 0.25, | |
| "leading_silence_s": 0.25, | |
| "trailing_silence_s": 0.25 | |
| }, | |
| "moe_impl": "sonic", | |
| "moe_n_experts": 16, | |
| "moe_router_topk": 1, | |
| "special_topk_layers": {"26": 2}, | |
| "moe_router_dim": 128, | |
| "moe_start_from_layer": 3, | |
| "moe_end_from_layer": 1 | |
| } | |