Skip to main content

ComfyUI "Value not in list" on a CLIP/text encoder — the missing LLM encoder

Also seen as: "Value not in list", "clip_name not in list", "QuadrupleCLIPLoader value not in list", "llava_llama3 not found ComfyUI"

Direct answer

How do I fix "Value not in list on a text encoder"?

A "Value not in list" error on a CLIP/encoder loader means the encoder file the workflow expects is not in your text_encoders folder, so the dropdown cannot select it. On modern models this is almost always the large LLM/VL encoder people forget — newer models pair a small CLIP with a big language encoder, and shipping one short triggers this.

Key facts

  • iThe model needs more encoders than you downloaded — HiDream needs four (including a ~8.5GB llama-3.1-8b), HunyuanVideo needs clip_l + llava_llama3, Qwen-Image needs Qwen-2.5-VL-7B, Z-Image needs Qwen-3-4B.
  • iThe encoder is present but under a slightly different filename than the workflow references — exact-name match is required.
  • iThe encoder went to the wrong folder instead of models/text_encoders.

Next step

  1. 1Identify the model’s full encoder set and download the one you are missing — it is usually the large LLM/VL encoder, not the CLIP.
  2. 2Match the exact filename the loader expects: t5xxl_fp8_e4m3fn.safetensors and t5xxl_fp8_e4m3fn_scaled.safetensors are different files, not interchangeable.
  3. 3Put encoders in models/text_encoders/ and restart so the dropdown repopulates.
  4. 4Not sure how many encoders a graph needs? A checker lists every model and encoder file the workflow references before you run it.

Not a fit when

  • Loaders enforce precision and packaging too — some Kijai loaders want a specific bf16 build and reject a scaled fp8 that native ComfyUI accepts. A file that is "basically right" can still fail.

Not sure this workflow will run before you rent a GPU?

Paste your ComfyUI workflow JSON into the free checker — it flags missing nodes, model requirements, and the VRAM/GPU you actually need. No signup.

Check my workflow freeSee GPU pricing

Other ComfyUI errors

Fix

GPU Memory Exhausted

Fix

Model Not Found

Fix

Missing Python Package

Fix

Disk Space Exhausted

Fix

Gated Model Access

Fix

missing custom nodes (node type not found)

Frequently Asked Questions

What causes "Value not in list on a text encoder" in ComfyUI?

The model needs more encoders than you downloaded — HiDream needs four (including a ~8.5GB llama-3.1-8b), HunyuanVideo needs clip_l + llava_llama3, Qwen-Image needs Qwen-2.5-VL-7B, Z-Image needs Qwen-3-4B.

How do I fix "Value not in list on a text encoder"?

Identify the model’s full encoder set and download the one you are missing — it is usually the large LLM/VL encoder, not the CLIP. Match the exact filename the loader expects: t5xxl_fp8_e4m3fn.safetensors and t5xxl_fp8_e4m3fn_scaled.safetensors are different files, not interchangeable.