Instructions to use dumpy50222/ComfyUI_LTX_Wan_Models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use dumpy50222/ComfyUI_LTX_Wan_Models with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="dumpy50222/ComfyUI_LTX_Wan_Models", filename="text_encoders/Gemma-4-E2B-Uncensored-HauhauCS-Aggressive-Q8_K_P.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 dumpy50222/ComfyUI_LTX_Wan_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 dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0 # Run inference directly in the terminal: llama cli -hf dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0 # Run inference directly in the terminal: llama cli -hf dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0
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 dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0
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 dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0
Use Docker
docker model run hf.co/dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0
- LM Studio
- Jan
- Ollama
How to use dumpy50222/ComfyUI_LTX_Wan_Models with Ollama:
ollama run hf.co/dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0
- Unsloth Studio
How to use dumpy50222/ComfyUI_LTX_Wan_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 dumpy50222/ComfyUI_LTX_Wan_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 dumpy50222/ComfyUI_LTX_Wan_Models to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for dumpy50222/ComfyUI_LTX_Wan_Models to start chatting
- Pi
How to use dumpy50222/ComfyUI_LTX_Wan_Models with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0
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": "dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use dumpy50222/ComfyUI_LTX_Wan_Models with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0
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 dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use dumpy50222/ComfyUI_LTX_Wan_Models with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0
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 "dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0" \ --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 dumpy50222/ComfyUI_LTX_Wan_Models with Docker Model Runner:
docker model run hf.co/dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0
- Lemonade
How to use dumpy50222/ComfyUI_LTX_Wan_Models with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull dumpy50222/ComfyUI_LTX_Wan_Models:Q8_0
Run and chat with the model
lemonade run user.ComfyUI_LTX_Wan_Models-Q8_0
List all available models
lemonade list
| { | |
| "file_name": "sulphur2Base_dev", | |
| "model_name": "Sulphur 2 Base", | |
| "file_path": "G:/AI/ComfyUI/models/diffusion_models/Sulphur2/sulphur2Base_dev.safetensors", | |
| "size": 29161842846, | |
| "modified": 1783552335.21189, | |
| "sha256": "41c999575859c528ff108022246a5524960a778c18742696971c9b0aadb4f70f", | |
| "base_model": "LTXV 2.3", | |
| "preview_url": "G:/AI/ComfyUI/models/diffusion_models/Sulphur2/sulphur2Base_dev.mp4", | |
| "preview_nsfw_level": 1, | |
| "notes": "", | |
| "from_civitai": true, | |
| "civitai": { | |
| "id": 2921800, | |
| "modelId": 2601098, | |
| "name": "Dev", | |
| "nsfwLevel": 19, | |
| "createdAt": "2026-05-05T21:18:48.701Z", | |
| "updatedAt": "2026-05-18T22:21:13.300Z", | |
| "status": "Published", | |
| "publishedAt": "2026-05-06T23:30:21.343Z", | |
| "trainedWords": [], | |
| "trainingStatus": null, | |
| "trainingDetails": null, | |
| "baseModel": "LTXV 2.3", | |
| "baseModelType": "Standard", | |
| "earlyAccessEndsAt": null, | |
| "earlyAccessConfig": null, | |
| "description": null, | |
| "uploadType": "Created", | |
| "usageControl": "Download", | |
| "licensingFee": null, | |
| "air": "urn:air:ltxv23:checkpoint:civitai:2601098@2921800", | |
| "stats": { | |
| "downloadCount": 2220, | |
| "thumbsUpCount": 145 | |
| }, | |
| "model": { | |
| "name": "Sulphur 2 Base", | |
| "type": "Checkpoint", | |
| "nsfw": false, | |
| "poi": false, | |
| "description": "<p><strong>Sulphur 2 Base</strong> is an uncensored, community-built video generation model on top of LTX 2.3. It runs text-to-video and image-to-video natively and supports every other LTX 2.3 format, with an optional prompt enhancer and distill LoRA in the same release.</p>\n<p><strong>Originally released by <a target=\"_blank\" rel=\"ugc\" href=\"https://huggingface.co/SulphurAI/Sulphur-2-base\">SulphurAI</a> on Hugging Face.</strong> All credit for the model goes to the SulphurAI team and contributors below. Civitai is hosting a mirror so creators can run it on-site - please head to the <a target=\"_blank\" rel=\"ugc\" href=\"https://huggingface.co/SulphurAI/Sulphur-2-base\">original repo</a> for weights, updates, and to support the project directly.</p>\n<h3 id=\"built-by\"><strong>Built by</strong></h3>\n<ul>\n <li><p><strong>SulphurAI</strong> - <a target=\"_blank\" rel=\"ugc\" href=\"https://huggingface.co/SulphurAI/Sulphur-2-base\">Hugging Face</a> | <a target=\"_blank\" rel=\"ugc\" href=\"https://discord.gg/GSXJhKZ9V\">Discord</a> | <a target=\"_blank\" rel=\"ugc\" href=\"https://ko-fi.com/fusioncow\">Ko-fi</a></p></li>\n <li><p><a target=\"_blank\" rel=\"ugc\" href=\"https://huggingface.co/TenStrip\">TenStrip</a> - testing and merging (<a target=\"_blank\" rel=\"ugc\" href=\"https://huggingface.co/TenStrip/LTX2.3-10Eros\">LTX2.3-10Eros i2v merge</a>)</p></li>\n <li><p><a target=\"_blank\" rel=\"ugc\" href=\"https://huggingface.co/silveroxides\">silveroxides</a> (<code>@s1lv3rc01n</code>) - testing, merging, quantizing</p></li>\n <li><p><code>@mov7162</code> - Musubi Tuner guidance</p></li>\n <li><p>Two anonymous funders who made the original Sulphur and Sulphur 2 possible</p></li>\n <li><p>Many other community contributors</p></li>\n</ul>\n<h3 id=\"native-t2v-and-i2v-on-ltx-23\"><strong>Native t2v and i2v on LTX 2.3</strong></h3>\n<p>Sulphur 2 inherits the LTX 2.3 pipeline end to end, so anything an LTX 2.3 workflow can do (t2v, i2v, the rest of the 2.3 formats) works here without extra glue. No converter nodes, no sidecar checkpoints.</p>\n<h3 id=\"versions-on-civitai\"><strong>Versions on Civitai</strong></h3>\n<ul>\n <li><p><strong>Dev</strong> - <code>fp8mixed</code> build for local runs that need VRAM headroom</p></li>\n <li><p><strong>Distilled</strong> - the included distill LoRA, ideal as the recommended starting point</p></li>\n</ul>\n<p>Pair the Dev version with the Distilled LoRA for the lightest setup. Existing workflows still reference <code>sulphur_final</code>. Use the LoRA <em>or</em> the full model, never both at the same time. The HF release also ships a <code>bf16</code> build, which is not currently mirrored on Civitai.</p>\n<h3 id=\"built-in-prompt-enhancer\"><strong>Built-in prompt enhancer</strong></h3>\n<p>A multimodal prompt enhancer ships with the model and is designed to drop straight into LM Studio:</p>\n<ol>\n <li><p>Open your LM Studio model folder.</p></li>\n <li><p>Create <code>Sulphur/promptenhancer/</code>.</p></li>\n <li><p>Drop the <code>.gguf</code> and <code>mmproj</code> files inside.</p></li>\n</ol>\n<p>LM Studio will pick it up on next launch. No system prompt is required, send the text (and an optional image) and it returns an enhanced prompt.</p>\n<h3 id=\"uncensored-by-design\"><strong>Uncensored by design</strong></h3>\n<p>Sulphur 2 is intentionally unfiltered for adult and creative work. Generations on Civitai still respect the site's content rules.</p>\n<h3 id=\"links\"><strong>Links</strong></h3>\n<ul>\n <li><p>Source: <a target=\"_blank\" rel=\"ugc\" href=\"https://huggingface.co/SulphurAI/Sulphur-2-base\">https://huggingface.co/SulphurAI/Sulphur-2-base</a></p></li>\n <li><p>Discord: <a target=\"_blank\" rel=\"ugc\" href=\"https://discord.gg/GSXJhKZ9V\">https://discord.gg/GSXJhKZ9V</a></p></li>\n <li><p>Support the project: <a target=\"_blank\" rel=\"ugc\" href=\"https://ko-fi.com/fusioncow\">https://ko-fi.com/fusioncow</a></p></li>\n</ul>", | |
| "tags": [ | |
| "base model" | |
| ], | |
| "allowNoCredit": true, | |
| "allowCommercialUse": [ | |
| "RentCivit", | |
| "Rent" | |
| ], | |
| "allowDerivatives": true, | |
| "allowDifferentLicense": true | |
| }, | |
| "files": [ | |
| { | |
| "id": 2802695, | |
| "sizeKB": 28478362.15429688, | |
| "name": "sulphur2Base_dev.safetensors", | |
| "overrideName": null, | |
| "type": "Model", | |
| "pickleScanResult": "Success", | |
| "pickleScanMessage": "No Pickle imports", | |
| "virusScanResult": "Success", | |
| "virusScanMessage": null, | |
| "scannedAt": "2026-05-06T19:53:47.114Z", | |
| "metadata": { | |
| "format": "SafeTensor", | |
| "size": "full", | |
| "fp": "fp8" | |
| }, | |
| "hashes": { | |
| "AutoV1": "E6E27450", | |
| "AutoV2": "41C9995758", | |
| "SHA256": "41C999575859C528FF108022246A5524960A778C18742696971C9B0AADB4F70F", | |
| "CRC32": "EAF5CD7C", | |
| "BLAKE3": "F71AD3FD2FC71E70744AE4DAD27D8B23DC525CC6C062ED84481A1CB9872A793B", | |
| "AutoV3": "875B03ACAE38" | |
| }, | |
| "primary": true, | |
| "downloadUrl": "https://civitai.red/api/download/models/2921800" | |
| } | |
| ], | |
| "images": [ | |
| { | |
| "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/4804a5cc-8020-4053-a8e2-b46faad3f72b/original=true/129884026.mp4", | |
| "nsfwLevel": 1, | |
| "width": 1152, | |
| "height": 768, | |
| "hash": "U9Fh3D?a57xt6R~B-p~A%gxaniOYEQI@xCs9", | |
| "type": "video", | |
| "metadata": { | |
| "hash": "U9Fh3D?a57xt6R~B-p~A%gxaniOYEQI@xCs9", | |
| "size": 1116211, | |
| "audio": false, | |
| "width": 1152, | |
| "height": 768, | |
| "duration": 5.042 | |
| }, | |
| "minor": false, | |
| "poi": false, | |
| "meta": null, | |
| "availability": "Public", | |
| "hasMeta": false, | |
| "hasPositivePrompt": false, | |
| "onSite": false, | |
| "remixOfId": null | |
| }, | |
| { | |
| "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/eee89be4-9055-4ae1-9f73-24823929ccd3/original=true/129882480.mp4", | |
| "nsfwLevel": 2, | |
| "width": 1152, | |
| "height": 768, | |
| "hash": "U9F~KtIU00?Z~V4TD%_3t7?a4n4nIA~qWY00", | |
| "type": "video", | |
| "metadata": { | |
| "hash": "U9F~KtIU00?Z~V4TD%_3t7?a4n4nIA~qWY00", | |
| "size": 2321171, | |
| "audio": false, | |
| "width": 1152, | |
| "height": 768, | |
| "duration": 5.042 | |
| }, | |
| "minor": false, | |
| "poi": false, | |
| "meta": null, | |
| "availability": "Public", | |
| "hasMeta": false, | |
| "hasPositivePrompt": false, | |
| "onSite": false, | |
| "remixOfId": null | |
| }, | |
| { | |
| "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/7eaf3f17-7b01-4e7c-95ee-3dfd71a369fd/original=true/131121028.mp4", | |
| "nsfwLevel": 16, | |
| "width": 1920, | |
| "height": 1056, | |
| "hash": "UTIiX.u%zA3STO=qWaR-M4Jjt1wN,^o[kURo", | |
| "type": "video", | |
| "metadata": { | |
| "hash": "UTIiX.u%zA3STO=qWaR-M4Jjt1wN,^o[kURo", | |
| "size": 13047064, | |
| "audio": false, | |
| "width": 1920, | |
| "height": 1056, | |
| "duration": 20.017 | |
| }, | |
| "minor": false, | |
| "poi": false, | |
| "meta": { | |
| "prompt": "workflow embedded. https://huggingface.co/bertbobson/Sulphur-2-base-INT8-ConvRot\nspeed increase for RTX 3xxx cards." | |
| }, | |
| "availability": "Public", | |
| "hasMeta": true, | |
| "hasPositivePrompt": true, | |
| "onSite": false, | |
| "remixOfId": null | |
| } | |
| ], | |
| "downloadUrl": "https://civitai.red/api/download/models/2921800", | |
| "creator": { | |
| "username": "FusionCow", | |
| "image": null | |
| } | |
| }, | |
| "tags": [ | |
| "base model" | |
| ], | |
| "modelDescription": "<p><strong>Sulphur 2 Base</strong> is an uncensored, community-built video generation model on top of LTX 2.3. It runs text-to-video and image-to-video natively and supports every other LTX 2.3 format, with an optional prompt enhancer and distill LoRA in the same release.</p>\n<p><strong>Originally released by <a target=\"_blank\" rel=\"ugc\" href=\"https://huggingface.co/SulphurAI/Sulphur-2-base\">SulphurAI</a> on Hugging Face.</strong> All credit for the model goes to the SulphurAI team and contributors below. Civitai is hosting a mirror so creators can run it on-site - please head to the <a target=\"_blank\" rel=\"ugc\" href=\"https://huggingface.co/SulphurAI/Sulphur-2-base\">original repo</a> for weights, updates, and to support the project directly.</p>\n<h3 id=\"built-by\"><strong>Built by</strong></h3>\n<ul>\n <li><p><strong>SulphurAI</strong> - <a target=\"_blank\" rel=\"ugc\" href=\"https://huggingface.co/SulphurAI/Sulphur-2-base\">Hugging Face</a> | <a target=\"_blank\" rel=\"ugc\" href=\"https://discord.gg/GSXJhKZ9V\">Discord</a> | <a target=\"_blank\" rel=\"ugc\" href=\"https://ko-fi.com/fusioncow\">Ko-fi</a></p></li>\n <li><p><a target=\"_blank\" rel=\"ugc\" href=\"https://huggingface.co/TenStrip\">TenStrip</a> - testing and merging (<a target=\"_blank\" rel=\"ugc\" href=\"https://huggingface.co/TenStrip/LTX2.3-10Eros\">LTX2.3-10Eros i2v merge</a>)</p></li>\n <li><p><a target=\"_blank\" rel=\"ugc\" href=\"https://huggingface.co/silveroxides\">silveroxides</a> (<code>@s1lv3rc01n</code>) - testing, merging, quantizing</p></li>\n <li><p><code>@mov7162</code> - Musubi Tuner guidance</p></li>\n <li><p>Two anonymous funders who made the original Sulphur and Sulphur 2 possible</p></li>\n <li><p>Many other community contributors</p></li>\n</ul>\n<h3 id=\"native-t2v-and-i2v-on-ltx-23\"><strong>Native t2v and i2v on LTX 2.3</strong></h3>\n<p>Sulphur 2 inherits the LTX 2.3 pipeline end to end, so anything an LTX 2.3 workflow can do (t2v, i2v, the rest of the 2.3 formats) works here without extra glue. No converter nodes, no sidecar checkpoints.</p>\n<h3 id=\"versions-on-civitai\"><strong>Versions on Civitai</strong></h3>\n<ul>\n <li><p><strong>Dev</strong> - <code>fp8mixed</code> build for local runs that need VRAM headroom</p></li>\n <li><p><strong>Distilled</strong> - the included distill LoRA, ideal as the recommended starting point</p></li>\n</ul>\n<p>Pair the Dev version with the Distilled LoRA for the lightest setup. Existing workflows still reference <code>sulphur_final</code>. Use the LoRA <em>or</em> the full model, never both at the same time. The HF release also ships a <code>bf16</code> build, which is not currently mirrored on Civitai.</p>\n<h3 id=\"built-in-prompt-enhancer\"><strong>Built-in prompt enhancer</strong></h3>\n<p>A multimodal prompt enhancer ships with the model and is designed to drop straight into LM Studio:</p>\n<ol>\n <li><p>Open your LM Studio model folder.</p></li>\n <li><p>Create <code>Sulphur/promptenhancer/</code>.</p></li>\n <li><p>Drop the <code>.gguf</code> and <code>mmproj</code> files inside.</p></li>\n</ol>\n<p>LM Studio will pick it up on next launch. No system prompt is required, send the text (and an optional image) and it returns an enhanced prompt.</p>\n<h3 id=\"uncensored-by-design\"><strong>Uncensored by design</strong></h3>\n<p>Sulphur 2 is intentionally unfiltered for adult and creative work. Generations on Civitai still respect the site's content rules.</p>\n<h3 id=\"links\"><strong>Links</strong></h3>\n<ul>\n <li><p>Source: <a target=\"_blank\" rel=\"ugc\" href=\"https://huggingface.co/SulphurAI/Sulphur-2-base\">https://huggingface.co/SulphurAI/Sulphur-2-base</a></p></li>\n <li><p>Discord: <a target=\"_blank\" rel=\"ugc\" href=\"https://discord.gg/GSXJhKZ9V\">https://discord.gg/GSXJhKZ9V</a></p></li>\n <li><p>Support the project: <a target=\"_blank\" rel=\"ugc\" href=\"https://ko-fi.com/fusioncow\">https://ko-fi.com/fusioncow</a></p></li>\n</ul>", | |
| "civitai_deleted": false, | |
| "favorite": false, | |
| "exclude": false, | |
| "db_checked": false, | |
| "skip_metadata_refresh": false, | |
| "metadata_source": "civitai_api", | |
| "last_checked_at": 1783735120.30088, | |
| "hash_status": "completed", | |
| "usage_tips": "{}", | |
| "sub_type": "checkpoint" | |
| } |