ltx-2.3-22b-distilled_transformer_only_bf16.safetensors
LTX 2.3 Distilled BF16 (Kijai)
BF16 distilled v1.0 transformer-only by Kijai. 44GB — requires 48GB VRAM or sequential offloading on 32GB.
Download ltx-2.3-22b-distilled_transformer_only_bf16.safetensors
Direct HuggingFace download. ~44 GB · Free.
No 32GB GPU? Try ltx-2.3-22b-distilled_transformer_only_bf16.safetensors online — free generation included
Skip the ~44 GB download and ComfyUI setup. Generate a 6-second video using this exact model in your browser, ~30 seconds.
Will this run on my GPU?
Minimum: 32GB VRAM.
Recommendation: Previous v1.0 BF16 distilled. Use v1.1 BF16 for latest quality. Enable Sequential Offloading on 32GB.
How to use ltx-2.3-22b-distilled_transformer_only_bf16.safetensors
- Download the file from HuggingFace.
- Place it in ComfyUI/models/checkpoints/ inside your ComfyUI directory.
- Restart ComfyUI (or refresh the model list from the menu).
- Load a compatible workflow — see below.
Compatible official workflows:
- LTX-2.3_T2V_I2V_Single_Stage_Distilled_Full.json— T2V / I2V Single Stage Distilled
- LTX-2.3_T2V_I2V_Two_Stage_Distilled.json— T2V / I2V Two Stage Distilled
- LTX-2.3_ICLoRA_Union_Control_Distilled.json— ICLoRA Union Control Distilled
- LTX-2.3_ICLoRA_Motion_Track_Distilled.json— ICLoRA Motion Track Distilled
- LTX-2.3_ICLoRA_HDR_Distilled.json— ICLoRA HDR Distilled
Don't want to run this locally? Try ltx-2.3-22b-distilled_transformer_only_bf16.safetensors online with a free generation — no GPU, no install, ~30 seconds per clip.
Common issues
ComfyUI doesn't see the file after I downloaded it▼
Make sure the file is in ComfyUI/models/checkpoints/ (not a subfolder). Restart ComfyUI fully — the menu refresh sometimes misses new files. Filename must match exactly: ltx-2.3-22b-distilled_transformer_only_bf16.safetensors.
CUDA out of memory error when loading the model▼
ltx-2.3-22b-distilled_transformer_only_bf16.safetensors needs ~32GB VRAM minimum. If you're hitting OOM: • Enable Sequential Offloading in ComfyUI settings • Lower the resolution (768×512 instead of 1280×704) — both dimensions must be divisible by 32 • Reduce frame count (65 frames instead of 161) — must be 8n+1 • Use a smaller variant — see Related models below.
What CFG and step count should I use?▼
Distilled models work best with CFG=1 and 8 sampling steps. Higher CFG or more steps with a distilled checkpoint produces over-saturated output and wastes time.
Get notified when LTX 2.3 Distilled BF16 (Kijai) updates
Occasional updates on what's new in LTX 2.3 — new FP8 quants, LoRAs, IC-LoRA releases — with our hands-on verdict on whether they're worth re-downloading. No fixed cadence.
No spam. Sent occasionally when there's real news. Unsubscribe in one click.
Related models
ltx-2.3-22b-distilled-1.1.safetensors
ltx-2.3-22b-distilled-1.1_transformer_only_bf16.safetensors
ltx-2.3-22b-dev.safetensors
ltx-2.3-22b-distilled.safetensors
ltx-2.3-22b-distilled-1.1.safetensors
ltx-2.3-22b-dev_transformer_only_bf16.safetensors