modele/Qwen-Image-Edit FP8 & GGUF - Q3_K_M.gguf

Qwen-Image-Edit FP8 & GGUF - Q3_K_M.gguf

11/23/2025

12:44:09 AM

Powiązane słowa kluczowe i tagi

base model,checkpoint,multimodal ai,q3_k_m.gguf,qwen,qwen edit,qwen image,qwen-image-edit,qwen-image-edit fp8 & gguf,qwen-vl,sweetmax797,text-guided image manipulation

Black and white portrait of a handsome dark-haired man sitting on a chair, wearing a black sweater and pants, looking upward while adjusting the black strap of a high-heeled shoe on a woman's leg, against a soft grey background.

A high-contrast portrait of a woman with her face split into black and white halves, separated by a golden zipper. She wears sharp golden nails and black leather gloves with thin wisps of smoke around her face.

Zalecane podpowiedzi

transform the image into 3D cartoon style, a war girl samurai cyborg robot, highly detailed, devil-armor, face mask, holding 1 heavy sword, detailed sword, the sword has a long hilt, grip the hilt, steady hold of the sword, (high kick:1.3) #### Fooocus: ['Misc Dystopian', 'Fooocus Masterpiece', 'Fooocus Negative', 'Fooocus Cinematic', 'Fooocus Photograph'] ####

Zalecane parametry

samplers

DPM++ 2M SDE Karras, Euler

steps

4 - 30

cfg

1 - 4

Wskazówki

Ensure the text encoder files have matching names: whatever_text-encoder.gguf should be paired with whatever_text-encoder_mmproj-F16.gguf to avoid errors.

Rename the mmproj file correctly if loading errors occur.

Check the FP8-optimized text encoder available at: https://civitai.com/models/1864281?modelVersionId=2110105

Use the GGUF workflow for best compatibility: https://civitai.com/models/1881851/qwen-iamge-edit-gguf-lightning-4steps-comfyui

Sponsorzy twórcy

Demo: https://chat.qwen.ai/

Text encoder FP8: https://civitai.com/models/1864281?modelVersionId=2110105

Workflow GGUF: https://civitai.com/models/1881851/qwen-iamge-edit-gguf-lightning-4steps-comfyui

Error: Can't find mmproj file for 'Qwen2.5-VL-7B-Instruct-Q3_K_M.gguf' (matching:'qwen2.5-vl-7b-instruct')! Qwen-Image-Edit will be broken!

Rename the mmproj-F16:

Make sure the downloaded text encoder has the correct file naming (whatever_text-encoder.gguf paired with whatever_text-encoder_mmproj-F16.gguf)

Demo: https://chat.qwen.ai/
Text encooder FP8: https://civitai.com/models/1864281?modelVersionId=2110105

Workflow GGUF: https://civitai.com/models/1881851/qwen-iamge-edit-gguf-lightning-4steps-comfyui

This FP8-optimized (e4m3fn) conversion of Qwen-Image-Edit, now fully compatible with the latest Qwen-VL image editing features! Leveraging Alibaba's advanced multimodal AI, this model enables seamless text-guided image manipulation, perfect for precise edits, prompt-based adjustments, and creative refinements. The model is mirrored here for convenience.