Modelpublic

ChrisColeTech/LTX-2.5-uncensored-v1.1-FP8

sourceHugging Faceunknownupdated 9d agoView on Hugging Face

56likes28kdownloads

Model Card

LTX Video-2.5 Extreme Uncensored Turbo v1.1 (Eros10 NSFW & 4-step LoRA baked-in)

UPDATED 9/10/2026:

—The latest LTX Video-2.5 Uncensored Turbo v1.1. fp8_scaled for speed.
—Uncensored Gemma4 12B text encoder w/ LTX projections baked-in (no extra files needed). int8 for speed and accuracy.

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

New in v1.1:

A pre-merged, GGUF and FP8 build of LTX Video-2.5 with five fine-tunes baked into the weights:

1.Eros10 NSFW LoRA - Eros10 is known for high quality, coherence, and Extreme NSFW (0.7 strength)
2.DMD Distilled LoRA - DMD distilled LoRA promises faster generations, better facial preservation (I2V), and MUCH better instruction following than v1 or stock ltx25. (1.0 strength)
3.LTX Video IC-LoRA - Official LTXV In-Context LoRA for better reference image adherence. (0.7 strength)
4.LTX Video IC-LoRA Detailer - Allows for video-to-video control on top of text-to-video and image-to-video (0.45 strength)
5.Img2Vid Lora - The BEST Img2Vid adapter for LTX-2, for better coherence and instruction following and easy I2V. (0.45 strength)

IC-LoRA Template Formatting (optional)

The IC LoRA is baked-in, use the template format for ultimate precision.

—Note: When invoking the IC-LoRA, the prompt must be formatted with the following tags:

[VISUAL]
[SPEECH]
[SOUNDS]

—Visual - Describe what is seen, and camera movement. LTX 2.5 supports multi-shots (ie. "start off front view close-up, then cut to a rear wide-view")
—Speech - Describe what is being said. Use [brackets] for audio cues during speech (ie. [screams] [laughs] [sighs] [grunts])
—Sounds - Describe what is audible or not audible (the model ignores "no music" so use "unscored" to enforce no background music.)

Samples - Text-to-Video (4-steps)

Text-to-Video works with as few as 4-steps, use 8-steps for the best results.

<table style="display: table; width: 100%; min-width: 100%; table-layout: fixed; text-align: center;"> <tr> <th style="text-align: center; width: 100%;"> T2V with speaking Example </th> </tr> <tr> <td style="text-align: center; width: 100%;"> Prompt: Cartoon-style 3D drawing of a cute girl with orange hair and black devil ears standing on a grassy hill under a bright blue sky with fluffy white clouds. She's wearing a red dress, has small black bat wings on her back, and a little black tail. "Look at me! I'm a little devil girl." "My red dress is simple and cute." "And check out these cool wings!" "And oh yeah, I have a little black tail too!" </td> </tr> <tr> <td style="text-align: center; width: 100%;"> <video controls style="display: block; width: 100%; min-width: 100%; object-fit: cover;" src="https://huggingface.co/ChrisColeTech/LTX-2.5-uncensored-v1.1-FP8/resolve/main/samples/ComfyUI00380.mp4"></video> <img src="https://huggingface.co/ChrisColeTech/LTX-2.5-uncensored-v1.1-FP8/resolve/main/samples/ComfyUI00380_strip.jpg"> </td> </tr>

</table>

a V12 supercar with neon lights underbody, speeding on a wet road. engine revs, turbo shifts, unscored b roll footage </td> </tr> <tr> <td style="text-align: center; width: 100%;"> <video controls style="display: block; width: 100%; min-width: 100%; object-fit: cover;" src="https://huggingface.co/ChrisColeTech/LTX-2.5-uncensored-v1.1-FP8/resolve/main/samples/ComfyUI00317.mp4"></video> <img src="https://huggingface.co/ChrisColeTech/LTX-2.5-uncensored-v1.1-FP8/resolve/main/samples/ComfyUI00317_strip.jpg"> </td> </tr>

</table>

Text-to-Video IC LoRA Prompt Template

<table style="display: table; width: 100%; min-width: 100%; table-layout: fixed; text-align: center;"> <tr> <th style="text-align: center; width: 100%;"> T2V with speaking IC LoRA Prompt Example </th> </tr> <tr> <td style="text-align: center; width: 100%;"> [VISUAL]: Cartoon-style 3D drawing of a cute girl with orange hair and black devil ears standing on a grassy hill under a bright blue sky with fluffy white clouds. She's wearing a red dress, has small black bat wings on her back, and a little black tail. The character is facing the camera directly with arms outstretched. Unscored footage. [SPEECH]: "Look at me! I'm a little devil girl." "My red dress is simple and cute." "And check out these cool wings!" "And oh yeah, I have a little black tail too!" [SOUNDS]: The girl's voice is playful and excited, her tone is high energy, like she's speaking directly to the viewer. Unscored </td> </tr> <tr> <td style="text-align: center; width: 100%;"> <video controls style="display: block; width: 100%; min-width: 100%; object-fit: cover;" src="https://huggingface.co/ChrisColeTech/LTX-2.5-uncensored-v1.1-FP8/resolve/main/samples/ComfyUI00430.mp4"></video> <img src="https://huggingface.co/ChrisColeTech/LTX-2.5-uncensored-v1.1-FP8/resolve/main/samples/ComfyUI00430_strip.jpg"> </td> </tr>

</table>

<table style="display: table; width: 100%; min-width: 100%; table-layout: fixed; text-align: center;"> <tr> <th style="text-align: center; width: 100%;"> T2V no speaking IC LoRA Prompt Example </th> </tr> <tr> <td style="text-align: center; width: 100%;"> [VISUAL]: epic drone shot side view, camera zooms out to aerial view. a V12 supercar with neon lights underbody, speeding on a wet road. [SOUNDS]: engine revs, turbo shifts, unscored b roll footage </td> </tr> <tr> <td style="text-align: center; width: 100%;"> <video controls style="display: block; width: 100%; min-width: 100%; object-fit: cover;" src="https://huggingface.co/ChrisColeTech/LTX-2.5-uncensored-v1.1-FP8/resolve/main/samples/ComfyUI00319.mp4"></video> <img src="https://huggingface.co/ChrisColeTech/LTX-2.5-uncensored-v1.1-FP8/resolve/main/samples/ComfyUI00319_strip.jpg"> </td> </tr>

</table>

Use the workflow Link

—Uses comfyui-gguf-loader custom_node

Samples - Image-to-Video

Image-to-Video is easy with this LTX 2.5 fine-tune (Img2Vid Adapter baked-in), just supply the image and the script, and the model handles the rest.

—Note: use 8-12 steps for best results.
—Higher CFG = more action, more audio, more talking.

Image-to-Video IC LoRA Prompt Template

Use the IC LoRA prompt format to control the action:

<table style="display: table; width: 100%; min-width: 100%; table-layout: fixed; text-align: center;"> <tr> <th style="text-align: center; width: 100%;" colspan=2> I2V IC LoRA Prompt Example </th> </tr> <tr> <td style="text-align: center; width: 100%;" colspan=2> [VISUAL]: seductive red headed filipina woman with black devil horns standing on a grassy hill under a bright blue sky with fluffy white clouds. She's wearing a sensual revealing red dress, has large black bat wings on her back, and a little black tail. [SPEECH]: "With L-T-X two-point-five, anything is possible!" [SOUNDS]: The girl's voice is playful and excited, her tone is high energy, like she's speaking directly to the viewer. Unscored </td> </tr> <tr> <td style="text-align: center; width: 100%;"> <img style="display: block; width: 512px; object-fit: cover;" src="https://huggingface.co/ChrisColeTech/LTX-2.5-uncensored-v1.1-FP8/resolve/main/samples/wildcards01450.png"> </td> <td style="text-align: center; width: 100%;"> <video controls style="display: block; width: 512px; object-fit: cover;" src="https://huggingface.co/ChrisColeTech/LTX-2.5-uncensored-v1.1-FP8/resolve/main/samples/ComfyUI00060.mp4"></video> </td> </tr> <tr> <td colspan=2> <img src="https://huggingface.co/ChrisColeTech/LTX-2.5-uncensored-v1.1-FP8/resolve/main/samples/ComfyUI00060_strip.jpg"> </td> </tr> </table>

Use the workflow Link

—Uses comfyui-gguf-loader custom_node
—Uses RTX Super Resolution custom_node

Recommended settings

Parameter	Value	Notes
`width` × `height`	1280 × 720	720P max resolution
`num_frames`	`124`	`960 max frames`
`frame_rate`	`24.0`
`steps`	`8`	8-steps minimum, 16 steps max
`guidance` / CFG	`1.0`	between 1.0 - 4.0 for best results
`negative_prompt`	(empty in samples)	optional

Components used to generate

Component	File	~Size	Download
Transformer	`ltx25_uncensored_v1.1-fp8_scaled.safetensors`	21.5 GB	Link
Text Encoder	`gemma4_12b_ltx25_uncensored-int8.safetensors`	13.2 GB	Link
Audio VAE	`ltx25_uncensored_v1.1_audio_vae.safetensors`	365 MB	Link
Video VAE	`ltx25_uncensored_v1.1_video_vae.safetensors`	1.47 GB	Link

—Note: These are ALL NEW files, NOT Sulphur

⚠ 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)