ltxv2b-q8-image-v1 · succeeded
LTX-Video 2B 0.9.8 distilled Q8_0 · seed 42
Download MP4 · 0.30 MiB
- Reference fox and snow remain recognizable across samples.
- Fox position and orientation change across the sampled frames, including a front-facing pose.
- A large tree appears and changes shape/position relative to the initial frame, indicating scene instability.
- First clip develops blurry/distorted fox anatomy near the end; second also changes scene and fox appearance.
Exact prompt
Animate the supplied image of the red fox in a snowy clearing. The fox walks steadily from left to right with clearly alternating leg steps and a gently swinging tail. Its body advances across the snow. Near the end it stops and turns its head toward the camera. Preserve the fox appearance and snowy forest setting from the reference image. Fixed wide camera, smooth continuous visible subject movement, one five-second shot, no cuts, no text.
Parameters and prompt details
{
"parameters": {
"2 CLIPLoaderGGUF": {
"clip_name": "t5-v1_1-xxl-encoder-Q4_K_M.gguf",
"type": "ltxv"
},
"1 UnetLoaderGGUFAdvanced": {
"unet_name": "ltxv-2b-0.9.8-distilled-Q8_0.gguf",
"dequant_dtype": "float32",
"patch_dtype": "float32",
"patch_on_device": false
},
"6 LTXVConditioning": {
"frame_rate": 24.0
},
"20 LoadImage": {
"image": "ltx-reference-fox.png"
},
"7 PFWholeStageLTXImage": {
"width": 512,
"height": 320,
"length": 121,
"batch_size": 1,
"strength": 1.0
},
"8 RandomNoise": {
"noise_seed": 42
},
"9 KSamplerSelect": {
"sampler_name": "euler"
},
"10 ManualSigmas": {
"sigmas": "1.0, 0.9937, 0.9875, 0.9812, 0.975, 0.9094, 0.725, 0.4219, 0.0"
},
"11 CFGGuider": {
"cfg": 1.0
},
"90 PFWholeStageDecode": {
"tile_size": 128,
"overlap": 32,
"temporal_size": 16,
"temporal_overlap": 8
},
"91 CreateVideo": {
"fps": 24.0
},
"92 SaveVideo": {
"format": "mp4",
"format.codec": "h264"
},
"3 VAELoader": {
"vae_name": "ltxv-2b-0.9.8-distilled-vae.safetensors"
}
},
"prompt_details": {
"conditioning_texts": {
"4.positive": "Create one video clip from the supplied scene description.\n\nSource generation_brief:\nAnimate the supplied image of the red fox in a snowy clearing. The fox walks steadily from left to right with clearly alternating leg steps and a gently swinging tail. Its body advances across the snow. Near the end it stops and turns its head toward the camera. Preserve the fox appearance and snowy forest setting from the reference image. Fixed wide camera, smooth continuous visible subject movement, one five-second shot, no cuts, no text.",
"4.negative": "frozen pose, motionless subject, static image, slideshow, blurry, distorted anatomy, flickering, subtitles, watermark"
},
"actual_positive_text": "Create one video clip from the supplied scene description.\n\nSource generation_brief:\nAnimate the supplied image of the red fox in a snowy clearing. The fox walks steadily from left to right with clearly alternating leg steps and a gently swinging tail. Its body advances across the snow. Near the end it stops and turns its head toward the camera. Preserve the fox appearance and snowy forest setting from the reference image. Fixed wide camera, smooth continuous visible subject movement, one five-second shot, no cuts, no text.",
"reference_image_path": "media/ltx-reference-fox.png"
}
}Timings, cache and resources
{
"timing": {
"factory_trace_seconds": 121.159132,
"comfy_server_seconds": 119.804,
"comfy_printed_seconds": null,
"stages_seconds": {
"text_encoder": 6.98399999999674,
"reference_image_encoder": 2.51500000001397,
"generator": 55.92200000002049,
"video_decoder": 42.01500000001397
},
"limits": "Factory trace and server totals have different boundaries. Observer node intervals include preparation/event delivery; not isolated kernel or weight-loading times."
},
"cache": {
"cached_nodes": [
"2",
"1",
"9",
"10",
"3"
],
"same_runtime_retained": true,
"immediate_warm_claim": null,
"context": "Image-input pair started after text pair in the same retained runtime; first image trial was already warm."
},
"resources": {
"sample_count": 61,
"scope": "Sampled values; GPU use is device-wide, not continuous per-process physical residency.",
"minimum_ram_available_bytes": 5559414784,
"minimum_commit_available_bytes": 15984709632,
"minimum_system_drive_free_bytes": 13855563776,
"maximum_gpu_total_used_mib": 5792
}
}Verification and checksums
{
"verification": {
"full_decode": true,
"checksum": true,
"acknowledged": true,
"trace_attachment": true,
"native_experiment": true,
"quality_scope": "Limited sampled review; no systematic full-resolution/per-trait/full-rate quality score.",
"independent_public_copy_decode": true
},
"media": [
{
"path": "media/ltx-03.mp4",
"mime_type": "video/mp4",
"size_bytes": 316588,
"sha256": "aef9f338efcd5b731d3b7568d8cabc9fb3085622e5b0e758aac9462420ac39e1",
"source_sha256": "213ff2c320654d334b1218e2b1f1d21ece95a26be6848500574ea6282cafd4aa",
"metadata_handling": "Container metadata stripped with stream copy; encoded audio/video streams not re-encoded.",
"width": 512,
"height": 320,
"duration_seconds": 5.041667,
"frames": 121,
"fps": 24.0,
"public_copy_full_decode_passed": true,
"source_content_preserved": "Encodedstream hashes identical aftermetadata-only remux"
}
]
}