Please be sure to update ComfyUI itself to the latest version.
v2.0 Prompt_Relay - Prompt-Relay has been implemented. Except for the positive prompt node, it is exactly the same as v2.0. If you want finer control over the prompts, this method is recommended, though it cannot be guaranteed to work perfectly.
v2.0 - Support for GGUF models has been added, and some 10Eros-Nodes have been implemented. Additionally, Distilled LoRA can now be disabled to allow the use of alternatives such as DMD LoRA. In the input area, it is now easy to configure settings such as the upscaled resolution, volume, number of steps for the Basic Scheduler, and Distilled LoRA weight.
v1.2 - Fixed connections related to the "LTXVCropGuides" node. Due to a lack of understanding of the "LTXVCropGuides" node, the connection method in v1.1 was incorrect. This error may have caused artifacts after upscaling under certain conditions, so this version has been updated, but it is not guaranteed to fix the problem.
Also, some configurations have been revised.
I noticed this issue when I tried to introduce a certain node into a new workflow, and severe artifacts occurred in my environment as well. Because the node connection method is different, it is not guaranteed that this workflow will be fixed, but I am releasing it for now.
v1.1 - Fixed an issue where the target FPS was being applied even when RIFE was not being used. Please enable only either "RIFE..." or "Don't Use..." on the FastGroupBypass node. Also, corrected an incorrect connection to the NAG node.
v1.0 - I've released the workflow I've been using for generation. However, please don't expect too much support from me.
●The safetensors model required for this workflow:
【Text Encoder】
coomfyUI/models/text_encoders
gemma_3_12B_it_fp8_scaled.safetensors （Some people also use fp4.）
https://huggingface.co/Comfy-Org/ltx-2/tree/main/split_files/text_encoders
or
Gemma_3_12B_it_ablit-norms-biproj-fp8mixed.safetensors
https://huggingface.co/TenStrip/LTX2.3-10Eros/tree/main/text_encoders
or
gemma-3-12b-it-heretic-v2_fp8_e4m3fn.safetensors
ltx_text_projection_bf16.safetensors
https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/text_encoders
(If using checkpoints that include CLIP, this is unnecessary.)
【VAE】
coomfyUI/models/vae
LTX23_audio_vae_bf16.safetensors
LTX23_video_vae_bf16.safetensors
(If using checkpoints that include VAE, this is unnecessary.)
taeltx2_3.safetensors
https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/vae
【Upscaler】(Be sure to select "1.1". "1.0" has a bug.)
ComfyUI/models/latent_upscale_models
Ltx-2.3-spatial-upscaler-x2-1.1.safetensors
https://huggingface.co/Lightricks/LTX-2.3/tree/main
●Recommended safetensors models for this workflow:
【Recommended Checkpoint】
(include CLIP & VAE version) comfyUI/models/checkpoint
ltx2310eros_v12.safetensors
ltx2310eros_v14.safetensors
https://civarchive.com/models/2447875/ltx23-10eros?modelVersionId=3109610
or
comfyUI/models/diffusion_models (GGUF … comfyUI/models/unet)
DasiwaLTX23_DragonleapV4.safetensors
https://civarchive.com/models/2543443/dasiwa-ltx-23?modelVersionId=3092188
【Distilled Lora】
ComfyUI/models/loras
Ltx-2.3-22b-distilled-lora-1.1_fro90_ceil72_condsafe.safetensors
https://huggingface.co/TenStrip/LTX2.3_Distilled_Lora_1.1_Experiments/tree/main
※ Recommended weights for Distilled LoRA
・ 10Eros v1.2 ... First Pass: 0.8–0.9, Upscale Pass: 0.5–0.6
・ Dasiwa Ltx2.3 v4 ... First Pass: 0.5–1.0, Upscale Pass: 0–0.5
Distilled LoRA and DMD LoRA serve similar functions, so do not enable them at the same time.
If the base model recommends DMD LoRA (such as 10Eros v1.4), enable only DMD LoRA and disable Distilled LoRA. For other base models, enable only Distilled LoRA and disable DMD LoRA.
【DMD Lora】
ComfyUI/models/loras
LTX2.3_DMD_reshaped_r256.safetensors
https://huggingface.co/TenStrip/LTX2.3_DMD_Lora/tree/main
※ Recommended weights for Distilled LoRA
・ 10Eros v1.4 ... 1.0
【OmniNFT Lora】
LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors
https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/loras
【comfy-nodes】
https://github.com/TenStrip/10S-Comfy-nodes
【Prompt-Relay】
https://github.com/kijai/ComfyUI-PromptRelay
Even when using the fp8 model, downloading all the necessary files will exceed 40GB. Because of this, you will likely encounter an Out of Memory error unless you have at least 64GB of system RAM. In fact, I hit OOM errors myself depending on the resolution and video length I tried.
Although using Prompt-Relay makes the workflow somewhat more complex, it offers significant benefits by enabling time-based prompting. It is a shame that it doesn't allow for dynamic adjustment of LoRA application—unlike the SVI feature in Wan2.2—but I consider it an essential node if you want to create videos that more faithfully match your vision.
Description
v1.1 - Fixed an issue where the target FPS was being applied even when RIFE was not being used. Please enable only either "RIFE..." or "Don't Use..." on the FastGroupBypass node.
Also, corrected an incorrect connection to the NAG node.
FAQ
Comments (19)
Great WF one of the best at keeping the orig. face from the image.
I have a question regarding this wf. In "Notes, power lora", it mentions OmniNFT and Edit Anything loras. I have both of them, but in the wf I can't find any dedicated loader to place them or any mention of the strength to use. Notes say first pass only, so would that mean put the loras in "power lora First" only?
I apologize, I simply forgot to correct the description in the previous version. Please ignore it. I'll quietly re-enter the data later.
Wait, the Director node affects video quality? First I'm hearing about it.. quite sad to hear, I haven't used it yet, but I was looking forward to using that node.
This is just my experience trying to implement it in my workflow, but it's true that I'm encountering a few problems. I think there might be something wrong with the upscaling path, but it could just be that I'm setting it up incorrectly, so it's too early to be discouraged.
@kenpechi Are you trying to use the LTX tiling sampler with it? I found it doesn't work because they conflict fundamentally in how they slice and process video math. So you are forced to use the normal Ksampler.
@ajreyz1384 Thanks, I knew right away that the Ltx tiling sampler was no good. The results were terrible. lol
However, there are other things that aren't working well, so I'm trying various things.
Thanks for the workflow !
RuntimeError: mat1 and mat2 must have the same dtype, but got Half and BFloat16
Something might not be clicking in the model area.
I don't have any issues with your other workflows. But here, no matter what I try, I keep getting the same error.
Looks nice, but when you disable interpolation it still takes the target FPS. Second you have you positive prompt go in for video to NAG instead of the negative one.
Thank you, you're absolutely right. I'll correct it.
where i put the upscaller? i create "latent_upscale_models" keep not reading
It's "models/latent_upscale_models," right? And of course, you've shut down and restarted ComfyUI, haven't you?
@kenpechi thx its work, but i need restart the pc XD....
by the way.. how make consistency? mine seem different while moving.. like asian to western
@saytolol12 Depending on the type of LORA, it may have been programmed for Westerners, so using it will gradually make you sound more Western. I think it's important to avoid over-reliance on LORA.
@kenpechi really? im use what you use on the workflow, except on power Lora nodes..
That is outside the scope of my responsibilities.