Instructions to use saik0s/comfy_backup with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use saik0s/comfy_backup with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="saik0s/comfy_backup", filename="ComfyUI/models/text_encoders/gemma-3-12b-it-q2_k.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 saik0s/comfy_backup 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 saik0s/comfy_backup:Q4_K_S # Run inference directly in the terminal: llama cli -hf saik0s/comfy_backup:Q4_K_S
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf saik0s/comfy_backup:Q4_K_S # Run inference directly in the terminal: llama cli -hf saik0s/comfy_backup: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 saik0s/comfy_backup:Q4_K_S # Run inference directly in the terminal: ./llama-cli -hf saik0s/comfy_backup: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 saik0s/comfy_backup:Q4_K_S # Run inference directly in the terminal: ./build/bin/llama-cli -hf saik0s/comfy_backup:Q4_K_S
Use Docker
docker model run hf.co/saik0s/comfy_backup:Q4_K_S
- LM Studio
- Jan
- Ollama
How to use saik0s/comfy_backup with Ollama:
ollama run hf.co/saik0s/comfy_backup:Q4_K_S
- Unsloth Studio
How to use saik0s/comfy_backup 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 saik0s/comfy_backup 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 saik0s/comfy_backup to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for saik0s/comfy_backup to start chatting
- Pi
How to use saik0s/comfy_backup with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf saik0s/comfy_backup:Q4_K_S
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": "saik0s/comfy_backup:Q4_K_S" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use saik0s/comfy_backup with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf saik0s/comfy_backup:Q4_K_S
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 saik0s/comfy_backup:Q4_K_S
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use saik0s/comfy_backup with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf saik0s/comfy_backup:Q4_K_S
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 "saik0s/comfy_backup:Q4_K_S" \ --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"
- Docker Model Runner
How to use saik0s/comfy_backup with Docker Model Runner:
docker model run hf.co/saik0s/comfy_backup:Q4_K_S
- Lemonade
How to use saik0s/comfy_backup with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull saik0s/comfy_backup:Q4_K_S
Run and chat with the model
lemonade run user.comfy_backup-Q4_K_S
List all available models
lemonade list
| <template> | |
| <div class="flex h-full flex-col gap-4 px-5"> | |
| <ResponseInput | |
| v-model="modelUrl" | |
| :allow-clear="true" | |
| :placeholder="$t('pleaseInputModelUrl')" | |
| @keypress.enter="searchModelsByUrl" | |
| > | |
| <template #suffix> | |
| <span | |
| class="pi pi-search text-base opacity-60" | |
| @click="searchModelsByUrl" | |
| ></span> | |
| </template> | |
| </ResponseInput> | |
| <!-- Direct file URL indicator with folder selection --> | |
| <div v-if="isDirectFile && modelUrl" class="flex flex-col gap-2"> | |
| <div | |
| class="flex items-center gap-2 rounded bg-green-50 p-2 text-sm text-green-600" | |
| > | |
| <i class="pi pi-check-circle"></i> | |
| <span>Direct file download detected</span> | |
| </div> | |
| <!-- Model Type/Folder Selection for direct downloads --> | |
| <div class="flex items-center gap-2"> | |
| <label class="text-sm font-medium">{{ $t('modelType') }}:</label> | |
| <ResponseSelect | |
| v-model="selectedModelType" | |
| :items="modelTypeOptions" | |
| :type="'drop'" | |
| class="flex-1" | |
| /> | |
| </div> | |
| </div> | |
| <div v-show="data.length > 0"> | |
| <ResponseSelect | |
| v-model="current" | |
| :items="data" | |
| :type="isMobile ? 'drop' : 'button'" | |
| > | |
| <template #prefix> | |
| <span>version:</span> | |
| </template> | |
| </ResponseSelect> | |
| </div> | |
| <ResponseScroll class="-mx-5 h-full"> | |
| <div class="px-5"> | |
| <KeepAlive> | |
| <ModelContent | |
| v-if="currentModel" | |
| :key="`${currentModel.id}-${currentModel.currentFileId}`" | |
| :model="currentModel" | |
| :editable="true" | |
| @submit="createDownTask" | |
| > | |
| <template #action> | |
| <div v-if="currentModel.files" class="flex-1"> | |
| <ResponseSelect | |
| :model-value="currentModel.currentFileId" | |
| :items="currentModel.selectionFiles" | |
| :type="isMobile ? 'drop' : 'button'" | |
| > | |
| </ResponseSelect> | |
| </div> | |
| <Button | |
| icon="pi pi-download" | |
| :label="$t('download')" | |
| type="submit" | |
| ></Button> | |
| </template> | |
| </ModelContent> | |
| </KeepAlive> | |
| <div v-show="data.length === 0"> | |
| <div class="flex flex-col items-center gap-4 py-8"> | |
| <i class="pi pi-box text-3xl"></i> | |
| <div>No Models Found</div> | |
| </div> | |
| </div> | |
| </div> | |
| </ResponseScroll> | |
| </div> | |
| </template> | |
| <script setup lang="ts"> | |
| import ModelContent from 'components/ModelContent.vue' | |
| import ResponseInput from 'components/ResponseInput.vue' | |
| import ResponseScroll from 'components/ResponseScroll.vue' | |
| import ResponseSelect from 'components/ResponseSelect.vue' | |
| import { useConfig } from 'hooks/config' | |
| import { useDialog } from 'hooks/dialog' | |
| import { useModelSearch } from 'hooks/download' | |
| import { useLoading } from 'hooks/loading' | |
| import { genModelFullName } from 'hooks/model' | |
| import { request } from 'hooks/request' | |
| import { useToast } from 'hooks/toast' | |
| import Button from 'primevue/button' | |
| import { VersionModel, WithResolved } from 'types/typings' | |
| import { | |
| getFilenameFromUrl, | |
| getModelTypeFromFilename, | |
| isDirectFileUrl, | |
| previewUrlToFile, | |
| } from 'utils/common' | |
| import { computed, ref, watch } from 'vue' | |
| const { isMobile } = useConfig() | |
| const { toast } = useToast() | |
| const loading = useLoading() | |
| const dialog = useDialog() | |
| const modelUrl = ref<string>() | |
| // Model type selection for direct downloads | |
| const selectedModelType = ref<string>('checkpoints') | |
| const modelTypeOptions = computed(() => [ | |
| { | |
| label: 'Checkpoints', | |
| value: 'checkpoints', | |
| command: () => { | |
| selectedModelType.value = 'checkpoints' | |
| }, | |
| }, | |
| { | |
| label: 'LoRA', | |
| value: 'loras', | |
| command: () => { | |
| selectedModelType.value = 'loras' | |
| }, | |
| }, | |
| { | |
| label: 'ControlNet', | |
| value: 'controlnet', | |
| command: () => { | |
| selectedModelType.value = 'controlnet' | |
| }, | |
| }, | |
| { | |
| label: 'VAE', | |
| value: 'vae', | |
| command: () => { | |
| selectedModelType.value = 'vae' | |
| }, | |
| }, | |
| { | |
| label: 'Embeddings', | |
| value: 'embeddings', | |
| command: () => { | |
| selectedModelType.value = 'embeddings' | |
| }, | |
| }, | |
| { | |
| label: 'Upscale Models', | |
| value: 'upscale_models', | |
| command: () => { | |
| selectedModelType.value = 'upscale_models' | |
| }, | |
| }, | |
| { | |
| label: 'Diffusers', | |
| value: 'diffusers', | |
| command: () => { | |
| selectedModelType.value = 'diffusers' | |
| }, | |
| }, | |
| { | |
| label: 'CLIP', | |
| value: 'clip', | |
| command: () => { | |
| selectedModelType.value = 'clip' | |
| }, | |
| }, | |
| { | |
| label: 'CLIP Vision', | |
| value: 'clip_vision', | |
| command: () => { | |
| selectedModelType.value = 'clip_vision' | |
| }, | |
| }, | |
| { | |
| label: 'UNet/Diffusion Models', | |
| value: 'diffusion_models', | |
| command: () => { | |
| selectedModelType.value = 'diffusion_models' | |
| }, | |
| }, | |
| { | |
| label: 'Style Models', | |
| value: 'style_models', | |
| command: () => { | |
| selectedModelType.value = 'style_models' | |
| }, | |
| }, | |
| { | |
| label: 'Hypernetworks', | |
| value: 'hypernetworks', | |
| command: () => { | |
| selectedModelType.value = 'hypernetworks' | |
| }, | |
| }, | |
| { | |
| label: 'GLIGEN', | |
| value: 'gligen', | |
| command: () => { | |
| selectedModelType.value = 'gligen' | |
| }, | |
| }, | |
| { | |
| label: 'PhotoMaker', | |
| value: 'photomaker', | |
| command: () => { | |
| selectedModelType.value = 'photomaker' | |
| }, | |
| }, | |
| { | |
| label: 'VAE Approx', | |
| value: 'vae_approx', | |
| command: () => { | |
| selectedModelType.value = 'vae_approx' | |
| }, | |
| }, | |
| { | |
| label: 'Classifiers', | |
| value: 'classifiers', | |
| command: () => { | |
| selectedModelType.value = 'classifiers' | |
| }, | |
| }, | |
| ]) | |
| const isDirectFile = computed(() => | |
| modelUrl.value ? isDirectFileUrl(modelUrl.value) : false, | |
| ) | |
| const { current, currentModel, data, search } = useModelSearch() | |
| const searchModelsByUrl = async () => { | |
| if (modelUrl.value) { | |
| const modelType = isDirectFile.value ? selectedModelType.value : undefined | |
| await search(modelUrl.value, modelType) | |
| } | |
| } | |
| // Watch for direct file URL changes and set intelligent default | |
| watch(modelUrl, (newUrl) => { | |
| if (newUrl && isDirectFileUrl(newUrl)) { | |
| const filename = getFilenameFromUrl(newUrl) | |
| const suggestedType = getModelTypeFromFilename(filename) | |
| selectedModelType.value = suggestedType | |
| } | |
| }) | |
| // Watch for model type changes on direct files and refresh the model | |
| watch(selectedModelType, async () => { | |
| if (isDirectFile.value && modelUrl.value) { | |
| await search(modelUrl.value, selectedModelType.value) | |
| } | |
| }) | |
| const createDownTask = async (data: WithResolved<VersionModel>) => { | |
| loading.show() | |
| const formData = new FormData() | |
| for (const key in data) { | |
| if (Object.prototype.hasOwnProperty.call(data, key)) { | |
| let value = data[key] | |
| // set preview file | |
| if (key === 'preview') { | |
| if (value) { | |
| const previewFile = await previewUrlToFile(value).catch(() => { | |
| loading.hide() | |
| toast.add({ | |
| severity: 'error', | |
| summary: 'Error', | |
| detail: 'Failed to download preview', | |
| life: 5000, | |
| }) | |
| throw new Error('Failed to download preview') | |
| }) | |
| formData.append('previewFile', previewFile) | |
| } else { | |
| formData.append('previewFile', value) | |
| } | |
| continue | |
| } | |
| if (typeof value === 'object') { | |
| value = JSON.stringify(value) | |
| } | |
| if (typeof value === 'number') { | |
| value = value.toString() | |
| } | |
| formData.append(key, value) | |
| } | |
| } | |
| const fullname = genModelFullName(data as VersionModel) | |
| formData.append('fullname', fullname) | |
| await request('/model', { | |
| method: 'POST', | |
| body: formData, | |
| }) | |
| .then(() => { | |
| dialog.close() | |
| }) | |
| .catch((e) => { | |
| toast.add({ | |
| severity: 'error', | |
| summary: 'Error', | |
| detail: e.message ?? 'Failed to create download task', | |
| life: 15000, | |
| }) | |
| }) | |
| .finally(() => { | |
| loading.hide() | |
| }) | |
| } | |
| </script> | |