Workflow Ltxv 13b 0 9 7 Fp8 I2v Portrait 512x928px To 1080x1920px

workflow_ltxv_13b_0_9_7_fp8_i2v_portrait_512x928px_to_1080x1920px

Imported workflow skill generated from LTXV 13b 0.9.7-FP8 i2v Portrait 512x928px to 1080x1920px.json.

Family

• video_t2v_i2v_avatar

Inputs

• Optional runtime overrides supported by run(...):
  • prompt
  • negative_prompt
  • width, height
  • seed, steps, cfg
  • sampler_name, scheduler, denoise
  • server, headers, api_prefix

Outputs

• Returns JSON with:
  • status
  • prompt_id
  • output_images

Model Requirements

• clip: t5xxl_fp16.safetensors -> models/clip
• checkpoint: ltxv-13b-0.9.7-distilled-fp8.safetensors -> models/checkpoints

Custom Node Requirements

• ComfyUI-LTXVideo
• comfyui-easy-use
• comfyui-kjnodes
• comfyui-videohelpersuite

Links

• https://discord.com/invite/gggpkVgBf3
• https://github.com/Lightricks/ComfyUI-LTXVideo/
• https://huggingface.co/Comfy-Org/mochi_preview_repackaged/resolve/main/split_files/text_encoders/t5xxl_fp16.safetensors?download=true
• https://huggingface.co/Comfy-Org/mochi_preview_repackaged/resolve/main/split_files/text_encoders/t5xxl_fp8_e4m3fn_scaled.safetensors?download=true
• https://huggingface.co/Lightricks/LTX-Video
• https://huggingface.co/Lightricks/LTX-Video/resolve/main/ltxv-13b-0.9.7-distilled-fp8.safetensors?download=true
• https://huggingface.co/Lightricks/LTX-Video/tree/main
• https://www.youtube.com/@pixaroma

Routing Metadata

• Family: video_t2v_i2v_avatar
• Input modalities: image, text_prompt
• Output modalities: video/mp4
• Model families: ltx
• Node count: 34
• Complexity score: 9
• Resource profile: very_high
• Estimated runtime: heavy (can exceed 6 min; best on high-VRAM GPU)
• Max latent resolution hint: NonexNone
• Max sampler steps hint: None

Detected Models

• clip: t5xxl_fp16.safetensors -> models/clip
• checkpoint: ltxv-13b-0.9.7-distilled-fp8.safetensors -> models/checkpoints

Detected Custom Nodes

• ComfyUI-LTXVideo
• comfyui-easy-use
• comfyui-kjnodes
• comfyui-videohelpersuite

Runtime Warnings

• Large model(s) detected; ensure enough VRAM and disk space.
• Multiple custom nodes required; verify node installation/version compatibility.
• Video workflow: usually slower and VRAM-intensive than still-image workflows.