# mossImage_sft_txt_int8.safetensors

> MOSS-Image text encoder (Qwen3.5 9B, int8) · Text encoder for MOSS-Image SFT and Base

mossImage_sft_txt_int8.safetensors is the Civitai download name of MOSS-Image’s int8 text encoder, qwen3.5_9b_int8_convrot.safetensors. mossImage_base_txt_int8.safetensors is the same file from the Base version. Put it in ComfyUI/models/text_encoders and load it with Load CLIP, type moss_image.

Comfy-Org’s repo has it as text_encoders/qwen3.5_9b_int8_convrot.safetensors. Either name works; pick it again in Load CLIP if your workflow uses the other.

## Facts

- **Same file as:** qwen3.5_9b_int8_convrot.safetensors
- **Type:** Text encoder
- **Format:** Safetensors · int8 convrot
- **Size:** 9.75 GB (9,748,121,532 bytes)
- **SHA256:** 32e3787472f708fa5f83624acbf5ef23f7fc89c439e05065ea57cfe5a97f025a
- **ComfyUI folder:** ComfyUI/models/text_encoders/
- **Loader node:** Load CLIP
- **License:** Apache-2.0
- **Released:** Oct 16, 2026 · Comfy-Org / Civitai release

## What is mossImage_sft_txt_int8.safetensors?

MOSS-Image, from OpenMOSS, conditions its images on Qwen3.5 9B rather than a CLIP or T5 encoder. Comfy-Org packages that encoder in three sizes: bf16 (19.3 GB), int8 convrot (9.75 GB) and w4a8 gptq (7.34 GB). This page is the int8 one.

Civitai’s official MOSS Image listing (model 3005406) carries the same text encoder in both its SFT and Base versions, with the SHA256 32e37874…5a97f025a that matches Comfy-Org’s file. Downloads from that listing were named after the version, mossImage_sft_txt_int8 and mossImage_base_txt_int8, which is why both names are searched. They are one file, so one copy serves both the SFT and Base diffusion models.

## Download and install

- [Hugging Face · Comfy-Org/MOSS-Image](https://huggingface.co/Comfy-Org/MOSS-Image/resolve/main/text_encoders/qwen3.5_9b_int8_convrot.safetensors) · saves as `qwen3.5_9b_int8_convrot.safetensors` · Official ComfyUI repackage, no sign-in. Rename if your workflow needs the Civitai name.
- [Civitai · MOSS Image (official)](https://civitai.com/models/3005406) · saves as `mossImage_sft_txt_int8.safetensors` · Same file in both the SFT and Base versions. Sign-in may be required.

```sh
cd ComfyUI/models/text_encoders
wget -O mossImage_sft_txt_int8.safetensors \
  https://huggingface.co/Comfy-Org/MOSS-Image/resolve/main/text_encoders/qwen3.5_9b_int8_convrot.safetensors
sha256sum mossImage_sft_txt_int8.safetensors
# 32e3787472f708fa5f83624acbf5ef23f7fc89c439e05065ea57cfe5a97f025a
```

Safetensors files hold tensors only and cannot run code. Still compare the SHA256: a failed download often leaves an HTML error page saved under the model’s filename.

## How to load it in ComfyUI

Load CLIP reads the text encoder and outputs a CLIP. Every prompt node in the graph encodes through it.

- **Set the type:** In Load CLIP choose type moss_image. Other types load the weights but encode prompts wrongly.
- **Less VRAM:** qwen3.5_9b_w4a8_gptq.safetensors (7.34 GB) is the smaller MOSS text encoder.

## Files a MOSS-Image workflow needs

- [`moss_image_sft_int8_convrot.safetensors`](https://huggingface.co/Comfy-Org/MOSS-Image/resolve/main/diffusion_models/moss_image_sft_int8_convrot.safetensors) · Diffusion model (SFT) · `models/diffusion_models/` · 5.41 GB
- [`flux2-vae.safetensors`](https://huggingface.co/Comfy-Org/MOSS-Image/resolve/main/vae/flux2-vae.safetensors) · VAE · `models/vae/` · 336 MB

## Workflows: Uses this exact file

These workflows already load mossImage_sft_txt_int8.safetensors. Open one and run it as is.

- [MOSS-Image Edit HQ | Single and Reference-Guided Editing](https://www.runcomfy.com/comfyui-workflows/moss-image-edit-hq-comfyui-text-and-reference-edits)

## Workflows: Uses another version of this file

These workflows load a different precision or format of the same model. Select mossImage_sft_txt_int8.safetensors in their Load CLIP node to use this version.

- [MiniMax H3 Image | Text to Image Generation](https://www.runcomfy.com/comfyui-workflows/minimax-h3-image-text-to-image-comfyui)
- [MiniMax H3 Image Editing ComfyUI | Guided Edits](https://www.runcomfy.com/comfyui-workflows/minimax-h3-comfyui-prompt-based-image-editing)
- [MOSS-Image Inpainting | Precise Local Image Edits](https://www.runcomfy.com/comfyui-workflows/moss-image-inpainting-comfyui-differential-diffusion)
- [MOSS-Image Base Layout-Guided Text to Image](https://www.runcomfy.com/comfyui-workflows/moss-image-base-in-comfyui-layout-guided-text-to-image)
- [MOSS-Image | Layout-Guided Text to Image](https://www.runcomfy.com/comfyui-workflows/moss-image-comfyui-bounding-box-text-to-image)
- [MOSS-Image Base Text to Image | Versatile Art](https://www.runcomfy.com/comfyui-workflows/moss-image-base-text-to-image-in-comfyui)
- [MOSS-Image | Text to Image Generator](https://www.runcomfy.com/comfyui-workflows/moss-image-comfyui-text-to-image)

## Same file, other names, and alternatives

- `mossImage_sft_txt_int8.safetensors` · This page · Civitai name (SFT) · 9.75 GB · MOSS-Image SFT and Base
- `mossImage_base_txt_int8.safetensors` · Identical bytes · Civitai name (Base) · 9.75 GB · Same file
- `qwen3.5_9b_int8_convrot.safetensors` · Identical bytes · Comfy-Org name · 9.75 GB · Same file
- `qwen3.5_9b_w4a8_gptq.safetensors` · Same encoder · w4a8 · 7.34 GB · Less VRAM
- `qwen3.5_9b_bf16.safetensors` · Same encoder · bf16 · 19.31 GB · Full precision

## Common errors and fixes

### Value not in list: clip_name: 'mossImage_sft_txt_int8.safetensors' not in [...]

Why: The workflow asks for this exact filename, but ComfyUI cannot find it in models/text_encoders. Usually the file is missing, sits in a different folder, or was saved under another name such as qwen3.5_9b_int8_convrot.safetensors.

Fix: Move the file into ComfyUI/models/text_encoders/, rename it to match the workflow (or pick it again in the dropdown), then refresh the node list or restart ComfyUI.

### SafetensorError: Error while deserializing header

Why: The download is incomplete, or the browser saved an HTML sign-in or error page under the model’s filename.

Fix: Check that the file is exactly 9,748,121,532 bytes and that its SHA256 matches the value above. Download it again from Hugging Face · Comfy-Org/MOSS-Image if not.

## FAQ

### Are mossimage_sft_txt_int8 and mossimage_base_txt_int8 different?

No. MOSS-Image SFT and Base share one text encoder. Civitai lists the same file, SHA256 `32e3787472f708fa5f83624acbf5ef23f7fc89c439e05065ea57cfe5a97f025a`, in both versions and only the download name changes.

### Which Load CLIP type should I pick?

`moss_image`.

### Where do I put mossImage_sft_txt_int8.safetensors in ComfyUI?

In `ComfyUI/models/text_encoders/`. Then refresh the node list or restart ComfyUI so Load CLIP lists the file.

### Which ComfyUI node loads mossImage_sft_txt_int8.safetensors?

[Load CLIP](/comfyui-nodes/ComfyUI/clip-loader). It is built into ComfyUI, so no custom nodes are needed.

### Can I use mossImage_sft_txt_int8.safetensors commercially?

Yes. MOSS-Image and its text encoder package are released under Apache-2.0.

## Sources

- [Comfy-Org/MOSS-Image](https://huggingface.co/Comfy-Org/MOSS-Image)
- [OpenMOSS-Team/MOSS-Image-SFT](https://huggingface.co/OpenMOSS-Team/MOSS-Image-SFT)
- [Civitai model 3005406](https://civitai.com/models/3005406)

Canonical page: https://www.runcomfy.com/comfyui-workflows/model-files/mossImage_sft_txt_int8.safetensors
