LTX-2.3-uncensored-v1.4-FP8

LTX Video-2.3 Uncensored Turbo v1.4 (Eros10 NSFW & 4-step LoRA baked-in)

UPDATED 8/21/2026 - The latest LTX Video-2.3 Uncensored Turbo v1.4 DiT with Distilled LoRA baked in.

Modes: img2video, txt2video, FL2VA / T2VA / I2VA / REF2VA/ AUDIO-TO-VIDEO.

New in v1.4:

A pre-merged, GGUF and FP8 build of LTX Video-2.3 with three fine-tunes baked into the weights:

1. Eros10 NSFW LoRA - Eros10 is known for high quality, coherence, and NSFW (1.0 strength)
2. DMD Distilled LoRA - DMD distilled LoRA promises faster generations, better facial preservation (I2V), and MUCH better instruction following than v1 or stock LTXV23. (1.0 strength)
3. LTX Video ICLoRA Detailer - Official LTXV In-Context LoRA for better reference image adherence. (0.6 strength)

---

Samples Text-to-Image (8-steps)

The model can produce video in as little as 4-steps, use 8-steps for best results.

<table style="width:100%;text-align: -webkit-center"> <tr><td style="align-content: center;"> <div> <video controls src="https://huggingface.co/ChrisColeTech/LTX-2.3-uncensored-fp8/resolve/main/samples/ComfyUI_00099_cfg_3_5.mp4"> </div> <img src="https://huggingface.co/ChrisColeTech/LTX-2.3-uncensored-v1.4-fp8/resolve/main/samples/ComfyUI_00099__strip.jpg"> </td></tr> <tr><td style="align-content: center;text-align: center"><strong>Prompt:</strong><br> cinematic tracking shot of a red sports car on a wet night street .<br> neon reflections, engine rumble and rain on asphalt.<br> shallow depth of field. </td></tr> </table>

Sample settings

• Note: Higher CFG = More motion and more audio

<table style="width:100%;text-align: -webkit-center"> <tr> <td style="align-content: center;"> <div> <video controls src="https://huggingface.co/ChrisColeTech/LTX-2.3-uncensored-fp8/resolve/main/samples/ComfyUI_00112_cfg1_0.mp4"> </div> <img src="https://huggingface.co/ChrisColeTech/LTX-2.3-uncensored-v1.4-fp8/resolve/main/samples/ComfyUI_00112_cfg1_0_strip.jpg"> </td> </tr> <tr><td style="align-content: center;text-align: center"><strong>CFG 1.0</strong><br> Best for <i>slow, sensual, sultry. <br> Intimate and personal. <br> No speaking. </i></td></tr> </table> <table style="width:100%;text-align: -webkit-center"> <tr> <td> <div> <video controls src="https://huggingface.co/ChrisColeTech/LTX-2.3-uncensored-fp8/resolve/main/samples/ComfyUI_00105_cfg_3_8.mp4"> </div> <img src="https://huggingface.co/ChrisColeTech/LTX-2.3-uncensored-v1.4-fp8/resolve/main/samples/ComfyUI_00105_cfg_3_8_strip.jpg"> </td> </tr> <tr><td style="align-content: center;text-align: center"><strong>CFG 3.8</strong><br> Best for <i>movie, cinema, action. <br> Dialog and sound.</i></td></tr> </table>

Link to workflow Link

---

Image-to-Video (9-steps)

This model excels at Image-to-Video while preserving the original identity.

<table style="text-align: -webkit-center"> <tr > <td style="align-content: center;text-align: center"><img src="https://huggingface.co/ChrisColeTech/minimax-h3-turbo-GGUF/resolve/main/samples/ComfyUI_00003.png" style="width:400px"></td> <td style="align-content: center;text-align: center"><video controls src="https://huggingface.co/ChrisColeTech/LTX-2.3-uncensored-fp8/resolve/main/samples/ComfyUI_00098_i2va.mp4" style="height:400px;"></video></td></tr> <tr><td colspan=2 style="align-content: center;text-align: center"><strong>Prompt:</strong> <br>Use this image as the first frame. <br>Make her fly. Full body shot. <br>High quality</td></tr> </table>

---

960 frames - 40s max (9-steps)

The model is very good at producing longer, high quality videos.

<table style="text-align: -webkit-center"> <tr > <td style="align-content: center;text-align: center"><img src="https://huggingface.co/ChrisColeTech/LTX-2.3-uncensored-fp8/resolve/main/samples/ComfyUI_01439.png" style="width:512px"></td> <td style="align-content: center;text-align: center"><video controls src="https://huggingface.co/ChrisColeTech/LTX-2.3-uncensored-v1.4-fp8/resolve/main/samples/ComfyUI_00175_.mp4" style="width:512px;"></video></td></tr> <tr><td colspan=2 style="align-content: center;text-align: center"><strong>Prompt:</strong> <br> Use this image as the starting frame and ending frame. <br> keeping sharp focus on the sensual red headed european woman in a wet tshirt and thong. <br> keep the character face, clothes and body consistent. <br> camera slowly does a constant zoom out to a full body shot. <br> she stands up and turns around facing away from the camera. <br> she shakes her ass and flirts a little. <br> she steps on the ledge and casually jumps into the pool, causing a moderate splash. <br> natural night light and sound ambiance for a hotel pool. <br> semi stable camera tracking smartphone style.<br> <br> she swims directly towards the camera. <br> she jumps onto the edge and climbs out of the pool. <br> she stands, hand on hips facing the camera for a second. <br> she turns around and faces away from the camera, hands at her side now. <br> she shakes her ass and teases a little. <br> then she turns back around, and faces the camera. <br> she sits down and ends up in the pose from the image as the last frame. <br> High quality</td></tr> </table>

• Note: Guardrails are in place to prevent illegal content, but mostly NSFW.

Link to workflow Link

---

Components used to generate

• Note: These are ALL NEW files, different from v1.0
• Clip Proj is required and goes in the text_encoders folder

---

⚠ Must use the updated GGUF Loader ⚠

In comfy:

• Open the ComfyUI Manager
• Change the channel to "Channel (remote)"
• and search for comfyui-gguf-loader
• download latest build (nightly)

---

Recommended settings

---