GGUF and INT8 ConvRot and INT4 W4A8 ConvRot quantizations of the UNET for ERNIE-Image: <a target="_blank" rel="ugc" href="https://huggingface.co/baidu/ERNIE-Image">https://huggingface.co/baidu/ERNIE-Image</a>NOTE: I did not make this model and I am not associated with it, I just quantized it using my CLI tool, <a target="_blank" rel="ugc" href="https://github.com/qskousen/ggufy">ggufy</a>.The text encoder is also available in INT8 or W4A8, listed below the Turbo model.The original BF16 text encoder and the VAE are also available from ComfyUI's hugging face: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/ERNIE-Image">https://huggingface.co/Comfy-Org/ERNIE-Image</a>(Note: Personally I had pretty poor results from the "prompt enhancer" model, and don't recommend using it.)PLEASE NOTE!If you are using the GGUF versions, ComfyUI-GGUF does NOT support this model yet! However, you can simply add "ernie" to the list of supported models and it will work. This is on line 12 of the file <code>custom_nodes/ComfyUI-GGUF/loader.py</code> and when you are done, it should look like this:<code>MG_ARCH_LIST = {"flux", "sd1", "sdxl", "sd3", "aura", "hidream", "cosmos", "ltxv", "hyvid", "wan", "lumina2", "qwen_image", "ernie"}</code>Recommended Settings:Sampler: eulerSchedule: simpleSteps: 20-50 (base), 8 (turbo)CFG: 2-4 (base), 1 (turbo)

Ernie / Ernie Turbo GGUF/Int8/Int4(W4A8)

ministral-3-3b-ASYM_W4A8_INT8.safetensors

ernie-image-turbo-ASYM_W4A8_INT8.safetensors

ernie-image-turbo-INT8_CONVROT.safetensors

ministral-3-3b-INT8_CONVROT.safetensors

ernie-image-turbo-q8_0.gguf

ernie-image-turbo-q4_k.gguf

ernie-image-turbo-q6_k.gguf

ERNIE-Image Turbo

ERNIE-Image

Files with SHA256: 51208f4191432688b610083fe0f3e19fc9210c84addd09cf30d5de669374c35d