HiDiffusion

ELLA

T5_TEXT_ENCODER

clip

CONDITIONING

CLIP Text Encode (Negative)

model

ella

CLIP Text Encode (Positive)

MODEL

samples

IMAGE

text_encoder

embeds

ELLA_EMBEDS

T5 Text Encode #Negative

positive

negative

latent_image

LATENT

images

ELLA Encode(Positive)

conditioning_to

conditioning_from

ELLA Encode(Negative)

T5 Text Encode #Positive

CLIP

andiamo

<p>A workflow that combines HiDiffusion ( <a href="https://github.com/blepping/comfyui_jankhidiffusion" target="_blank">https://github.com/blepping/comfyui_jankhidiffusion</a> ) and ELLA ( <a href="https://github.com/TencentQQGYLab/ComfyUI-ELLA/tree/main/examples" target="_blank">https://github.com/TencentQQGYLab/ComfyUI-ELLA/tree/main/examples</a> ). </p><p>This workflows is compatible with SD1.5 and it can be used to generate high resolution images with a decent prompt adherence.</p>

HiDiffusion SD1.5 + ELLA: High Resolution and Good Prompt Adherence

OpenArt

Workflows

Active Sessions

HiDiffusion SD1.5 + ELLA: High Resolution and Good Prompt Adherence

Description

Discussion

Loading...