Bedovyy

/

ERNIE-Image-Quantized

like 15

Have you tried original BF16 and does it works properly?
Could you let me know information about your GPU, ComfyUI version (and CUDA version if your GPU is nVidia's)?

I have tested latest version of ComfyUI by git pull, by the way.

the NVFP4 version works flawlessly with the official comfy wf. (But you have to disable the prompt enhancer; it's badly implemented. Somebody knows what model the enhancer is based on?). Thanks for your quants ;-)

PE is based on Mistral3-3B, the same as text encoder.
https://huggingface.co/baidu/ERNIE-Image/blob/main/pe/config.json

Nice work！I try to use the follow configuration，and just replace the ernie-image-turbo.safetensors with your fp8 safetensors，but it only generates noisy images。Could you please help me？
https://huggingface.co/Comfy-Org/ERNIE-Image
📂 ComfyUI/
├── 📂 models/
│ ├── 📂 diffusion_models/
│ │ ├── ernie-image.safetensors
│ │ └── ernie-image-turbo.safetensors
│ ├── 📂 text_encoders/
│ │ ├── ernie-image-prompt-enhancer.safetensors
│ │ └── ministral-3-3b.safetensors
│ └── 📂 vae/
│ └── flux2-vae.safetensors

you may misuse PE fp8 as clip? I got noisy images when doing this. ernie-image-turbo-fp8.safetensors works well on my device

Have you tried original BF16 and does it works properly?
Could you let me know information about your GPU, ComfyUI version (and CUDA version if your GPU is nVidia's)?

I have tested latest version of ComfyUI by git pull, by the way.

Thanks a lot，after changed to ernie-image workflow template, it works fine.
Noisy images ( only because i used wrong workflow template: z-image).

the NVFP4 version works flawlessly with the official comfy wf. (But you have to disable the prompt enhancer; it's badly implemented. Somebody knows what model the enhancer is based on?). Thanks for your quants ;-)

yeah, i disabled PE, it works fine now. i think you can use grok to replace PE, so that you can generate nsfw pics.