PlagueKind - LTX2.3 Workflow - I2V - NVFP4 | MXFP8 | Ease of use
V1 Notes
Focused Mainly on Speed and ease of usability while retaining single pass quality and likeness.
First pass is more or less optimized.
Identity Retention is pretty good.
First pass balanced for speed and quality.
Upscale and 2x fps work but will be optimized later.
I would avoid using RTX VSR with the whole chain active unless you have like 96gb ram.
Nvfp4 models are only for Blackwell, using them will not save you speed if you don't have Blackwell, but they should still work.
Default settings of the first pass should produce good quality and sharp. I personally like to use this for a single pass and just render straight at 1280.
Bumped FPS to 30 because it looks way bettwen imo, quality seems clearer overall and it gets rid of that ltx base fps look.
Memory Chunk Note
This saves vram and speeds up it/s especially on longer videos
With 16gb of VRAM 3 chunks seems optimal for me
If you get triton errors, enter the model loader subgraph and disable use triton kernels
Requirements
Sage Attention (optional)
Model Choices
ltx-2.3-22b-dev-nvfp4.safetensors
ltx-2.3-22b-dev_transformer_only_mxfp8_block32.safetensors
Latent Upscalers
ltx-2.3-spatial-upscaler-x2-1.1.safetensors
ltx-2.3-temporal-upscaler-x2-1.0.safetensors
VAE
LTX23_audio_vae_bf16.safetensors
LTX23_video_vae_bf16.safetensors
Dual CLIP (Encoder and Projection) Choices
gemma_3_12B_it_fp4_mixed.safetensors
gemma_3_12B_it_fp8_scaled.safetensors
ltx-2.3_text_projection_fp8.safetensors
ltx-2.3_text_projection_bf16.safetensors
Distilled LoRA
ltx-2.3-22b-distilled-lora-1.1_fro90_ceil72_condsafe.safetensors
Optional LoRA
LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors
LTX_SulphurEXP_LoRA_fro99-avgrank105.safetensors
LTX_10Eros_LoRA_fro99-avgrank77.safetensors
Optional Model converted by me
Model tree for Plaguekind/ltx2.3
Base model
Kijai/LTX2.3_comfy