【LTX2】IMG to VIDEO - v1.0

Hello, just a quick note to let you know that I created this workflow under complex conditions. I don't have my usual system and am forced to rent runpods for my tests. I haven't been able to perform as many checks and tests as usual, so please don't hesitate to send me a message if you encounter any problems.

Description:

This workflow allows you to generate video a base image and a text.

Resources you need:

📂Files :

LTX2 Quant Model: Q8, Q6, Q5, Q4, Q3 (i recommend Q5)
In models/unet

MelBandRoFormer : MelBandRoformer_fp32.safetensors
in models/diffusion_models

GEMMA-3: Q8, Q6, Q5, Q4, Q3 (i recommend Q4)
in models/clip

TEXT ENCODER: ltx-2-19b-embeddings_connector_dev_bf16.safetensors
in models/clip

VIDEO VAE: TX2_video_vae_bf16.safetensors
in models/vae
AUDIO VAE: LTX2_audio_vae_bf16.safetensors
in models/vae

Upscale model: ltx-2-spatial-upscaler-x2-1.0.safetensors
in models/latent_upscale_models

Recommanded LoRA:

in models/loras

📦Custom Nodes :

Description

base version

FAQ

Comments (12)

BrownRecluse666Jan 23, 2026· 6 reactions

CivitAI

Thank you for the links to all the files, it makes it so much easier than having to track them all down!

ApchXiJan 23, 2026

CivitAI

Hi .Problen with Clip Loader # ComfyUI Error Report ## Error Details - **Node ID:** 15 - **Node Type:** DualCLIPLoaderGGUF - **Exception Type:** ValueError - **Exception Message:** Unexpected text model architecture type in GGUF file: 'gemma3' ## Stack Trace ``` File "D:\COMFYUI\comfyuiAutoInstallerWAN21_v25\ComfyUI_windows_portable\ComfyUI\execution.py", line 518, in execute output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\COMFYUI\comfyuiAutoInstallerWAN21_v25\ComfyUI_windows_portable\ComfyUI\execution.py", line 329, in get_output_data return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\COMFYUI\comfyuiAutoInstallerWAN21_v25\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-lora-manager\py\metadata_collector\metadata_hook.py", line 165, in async_map_node_over_list_with_metadata results = await original_map_node_over_list( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\COMFYUI\comfyuiAutoInstallerWAN21_v25\ComfyUI_windows_portable\ComfyUI\execution.py", line 303, in _async_map_node_over_list await process_inputs(input_dict, i) File "D:\COMFYUI\comfyuiAutoInstallerWAN21_v25\ComfyUI_windows_portable\ComfyUI\execution.py", line 291, in process_inputs result = f(**inputs) ^^^^^^^^^^^ File "D:\COMFYUI\comfyuiAutoInstallerWAN21_v25\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\nodes.py", line 266, in load_clip return (self.load_patcher(clip_paths, clip_type, self.load_data(clip_paths)),) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\COMFYUI\comfyuiAutoInstallerWAN21_v25\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\nodes.py", line 220, in load_data sd = gguf_clip_loader(p) ^^^^^^^^^^^^^^^^^^^ File "D:\COMFYUI\comfyuiAutoInstallerWAN21_v25\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\loader.py", line 378, in gguf_clip_loader sd, arch = gguf_sd_loader(path, return_arch=True, is_text_model=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\COMFYUI\comfyuiAutoInstallerWAN21_v25\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\loader.py", line 89, in gguf_sd_loader raise ValueError(f"Unexpected text model architecture type in GGUF file: {arch_str!r}")

UmeAiRT

Author

Jan 23, 2026

Is your ComfyUI up to date?

ApchXiJan 24, 2026

@UmeAiRT yes

ApchXiJan 24, 2026

@UmeAiRT node DualClipLoader GGUF dont support LTX2. Not working

aibillybobJan 24, 2026

@ApchXi update your GGUF loaders in the comfyui manager installed nodes, update to latest. Worked for me!

SirkuraJan 23, 2026

CivitAI

I wondered if you happend to have any workflows for illustrius. i've found character loras for that that i can't find for other models.

UmeAiRT

Author

Jan 24, 2026

I have more than 5 workflows for Illustrious : https://civitai.com/collections/14887413

SirkuraJan 25, 2026

@UmeAiRT oh thank you! I had heard that SD wasn't the same model as illustrius not compatible. I actually have these workflows!

I aso had another question, is there something similar to PuLID that works for blackwell GPU's? I saw that workflow was depreciated. i'm looking for something that could do image to image or keep a face consistant in generation making smaller edits. masks seem to only do so much. i was looking for a bit more control over the imaging.

TenzanJan 26, 2026

CivitAI

Good workflow. Face consistency from image when talking seems not great most of the time, OK sometimes. Anything to combat this?

majidzendaniyan714Feb 23, 2026

CivitAI

gemma 3 12B it fp8 Text Encoder Not yet working ?

raise ValueError(f"Unexpected text model architecture type in GGUF file: {arch_str!r}")

ValueError: Unexpected text model architecture type in GGUF file: 'gemma3'

hithatwhitham895Mar 25, 2026

CivitAI

having trouble

RuntimeError: mat1 and mat2 shapes cannot be multiplied (1024x3840 and 1920x4096)

Workflows