QWEN IMAGE EDIT NEW MULTIMODAL AI IMAGE EDITING KING WORKFLOW!
Added 2025-08-21 19:27:52 +0000 UTCHey everyone! I've just released a new video on "THE NEW MULTIMODAL AI KING!", called "QWEN IMAGE EDIT" made by the same team that created Qwen image. A multimodal model that is able to automatically edits images with incredible precision and that follows your prompt better than Kontext.
You can check out the video right here: https://youtu.be/6EVVV2lUMFU
I also created a 1-click installer for the Webui for my Patreon supporters for Local AND Runpod, that you can find right here: https://www.patreon.com/posts/137036485
Here the link to the manual install guide: https://pastebin.com/aYMsWDmr
Down below you will also find the QWEN_IMAGE_EDIT_WORKFLOW.json for free for you to use!
As always, supporting me on Patreon allows me to keep creating helpful resources like this for the community. Thank you for your support - now go have some fun😉!
Comments
It's not NSFW, when you remove the clothes, an intimate "clothing" is added.
GreonoGames
2025-09-18 00:14:57 +0000 UTCHow do I change the seed to be random?
Jordan Freeman
2025-09-15 13:33:37 +0000 UTCAbout mat1 mat2 error: https://github.com/comfyanonymous/ComfyUI/issues/9423 "It's GGUF node issue. Replace "ClipLoaderGGUF" with "Load Clip" and download qwen_2.5_vl_7b_fp8_scaled.safetensors" https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/text_encoders Configure loadclip with the file above in models/clip and type qwen_image Device: default
Carlos H A Silva
2025-08-31 01:36:01 +0000 UTCI also have the same error. I solved by using normal Load CLIP node using the qwen_2.5_vl_7b_fp8_scaled.safetensor also don't forget to change the type to qwen _image
W4v3r1d3r
2025-08-29 14:25:56 +0000 UTCerror: TextEncodeQwenImageEdit mat1 and mat2 shapes cannot be multiplied (5292x1280 and 3840x1280)
Bob
2025-08-29 10:13:08 +0000 UTCSo.. Any LORAs for Qwen Image-Edit?? There's a LORA Trainer for Image-Edit (yes, for EDIT) but I can only find 1 or 2 LORAs. [TRAINER: LoRA Training for Qwen-Image & Qwen-Image-Edit : https://github.com/FlyMyAI/flymyai-lora-trainer]
Alan Smile
2025-08-24 10:06:11 +0000 UTCsooooo for anyone having the "shape '[1, 16, 51, 2, 80, 2]' is invalid for input of size 4177920" to error, if you look over to the right of the model loader. make sure the qwen vae is selected. even if you see it open it again and select the qwen_image_vae.
corey L
2025-08-23 16:28:47 +0000 UTCHow to keep the Characters consistent. I get everytime a different set of people.
Killy_Blame
2025-08-22 18:55:42 +0000 UTCHey! It perfectly works for me on Runpod! Is there a way to download LoRas directly from Runpod interface? To avoid upload in the pod manually? It's very looooooong.... and slooooooow....
RavenWT
2025-08-22 16:17:29 +0000 UTC
