Audio vae for TFO model
", "uploadType": "Created", "usageControl": "Download", "licensingFee": null, "air": "urn:air:ltxv2:checkpoint:civitai:2445970@2750820", "stats": { "downloadCount": 592, "thumbsUpCount": 12 }, "model": { "name": "LTX2.3 FP4", "type": "Checkpoint", "nsfw": false, "poi": false, "description": "LTX2.3 Distilled FP4ME - Distilled FP4 Mixed Extreme - 14.1GB**
LTX2.3 Full Dev FP4ME - Full Dev FP4 Mixed Extreme - 14.1GB**
LTX2.3 Official NVFP4 - From Lightricks - Updated 3/17/2026 - 21GB
LTX2.3 Dev NVFP4 - from Hippotes / LTX-2.3-various-formats - 18.15GB
LTX2.3 Dev FP4 STFO - from Kijai's Transformers only Scaled FP8 - 16.63GB**
LTX2.3 Distilled FP4 - My first FP4 - Transformers Only - 18.15GB**
** Are transformers only, or I broke vae/text projection :) needs seperate Vae and Text projection downloads.
I have a fix for lora issue on FP4ME models. Comfy Bathroom, custom lora loader with presets as well as custom config. https://huggingface.co/MrReclusive/LTX-2.3-FP4
Diffusion model loader/unet loader seems to get confused with these, use the checkpoint loader even though it has no clip/vae
", "tags": [ "ltx2", "base model", "ltx2.3", "fp4" ], "allowNoCredit": true, "allowCommercialUse": [ "Image", "RentCivit", "Rent" ], "allowDerivatives": true, "allowDifferentLicense": true }, "files": [ { "id": 2637308, "sizeKB": 356303.89453125, "name": "ltx23FP4_ltx23AudioVae.safetensors", "type": "Model", "pickleScanResult": "Success", "pickleScanMessage": "No Pickle imports", "virusScanResult": "Success", "virusScanMessage": null, "scannedAt": "2026-03-07T03:15:33.023Z", "metadata": { "format": "SafeTensor", "size": "full", "fp": "bf16" }, "hashes": { "AutoV1": "1324F6CB", "AutoV2": "5BC10FA4AD", "SHA256": "5BC10FA4ADECF99DDA132D916E23048CBD56797702C5FA50EB5D2079048A38C3", "CRC32": "EA02D754", "BLAKE3": "3215B775195E9306B7B704970D9B5D15AB40CA42AC5AA861574E83ABEA130684", "AutoV3": "28CEB51ED018" }, "primary": true, "downloadUrl": "https://civitai.red/api/download/models/2750820" } ], "images": [ { "url": "https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/803c5d4c-b254-47fd-b6e9-0f3b113f79fa/original=true/123401038.mp4", "nsfwLevel": 1, "width": 1280, "height": 640, "hash": "UAAJ~8MwD%-:~oM|D*WU_2M|IUoe_2adIUxZ", "type": "video", "metadata": { "hash": "UAAJ~8MwD%-:~oM|D*WU_2M|IUoe_2adIUxZ", "size": 5073813, "audio": true, "width": 1280, "height": 640, "duration": 9.75 }, "minor": false, "poi": false, "meta": { "prompt": "Style: cinematic-realistic with muted color palette. A young woman with striking features walks down a busy city street, oblivious to her surroundings as she intensely focuses on her phone. Her long, dark hair cascades down her back like a waterfall of night, framing a pale complexion adorned with subtle freckles and bold, black eyeliner. She wears a fitted, high-collared black dress that accentuates her slender figure, drawing attention to the intricate lace patterns on its hem. The woman's eyes are glued to the screen, her expression one of absorption rather than concern for her environment. As she stumbles forward, passersby weave around her without noticing her impending collision with a large, colorful sign featuring an animated bong in the foreground. With a comical jolt, the woman collides with the sign, causing her to lose balance and tumble backward onto the pavement with a soft thud. Her phone goes flying from her grasp as she lets out a startled \"Oww\" in a deep, throaty voice, her eyes widening with surprise. The sound of scuffling footsteps echoes through the area, followed by the muted murmur of onlookers' concerned whispers. Amidst this commotion, a city bus rumbles by in the background, releasing a gentle whoosh of air as it passes, while the soundscape is also filled with distant traffic hum and muffled conversations from nearby pedestrians. As the woman struggles to stand up, brushing off her dress with a hint of embarrassment, text appears on screen at the bottom, displayed in a playful, sans-serif font: 'Don't Text & Adult'. The words remain for several seconds before fading out as the scene gradually returns to the bustling city atmosphere, the woman's expression now one of sheepishness and awareness." }, "availability": "Public", "hasMeta": true, "hasPositivePrompt": true, "onSite": false, "remixOfId": null } ], "downloadUrl": "https://civitai.red/api/download/models/2750820", "creator": { "username": "MrReclusive666", "image": null } }, "tags": [ "ltx2", "base model", "ltx2.3", "fp4" ], "modelDescription": "LTX2.3 Distilled FP4ME - Distilled FP4 Mixed Extreme - 14.1GB**
LTX2.3 Full Dev FP4ME - Full Dev FP4 Mixed Extreme - 14.1GB**
LTX2.3 Official NVFP4 - From Lightricks - Updated 3/17/2026 - 21GB
LTX2.3 Dev NVFP4 - from Hippotes / LTX-2.3-various-formats - 18.15GB
LTX2.3 Dev FP4 STFO - from Kijai's Transformers only Scaled FP8 - 16.63GB**
LTX2.3 Distilled FP4 - My first FP4 - Transformers Only - 18.15GB**
** Are transformers only, or I broke vae/text projection :) needs seperate Vae and Text projection downloads.
I have a fix for lora issue on FP4ME models. Comfy Bathroom, custom lora loader with presets as well as custom config. https://huggingface.co/MrReclusive/LTX-2.3-FP4
Diffusion model loader/unet loader seems to get confused with these, use the checkpoint loader even though it has no clip/vae
", "civitai_deleted": false, "favorite": false, "exclude": false, "db_checked": false, "skip_metadata_refresh": false, "metadata_source": "civitai_api", "last_checked_at": 1782019053.220402, "hash_status": "completed", "usage_tips": "{}", "sub_type": "checkpoint" }