Flux.2 Klein 9B UPDATE - SEE VERSION DETAILSQWEN IMAGE EDIT v2511 UPDATE - SEE VERSION DETAILSFirstly, this is a concept that Qwen Image Edit (and Flux.2 Klein 9B) can do already, kind of. It's pretty good at Outpainting by using the prompt <code>Remove the white parts</code>. You can even add a context image, but for Qwen Image Edit it's not great/doesn't work the best. Look at the examples for ideas of what it can help with. This was trained exclusively on photos, but seems to work for anime as well. Trained using <a target="_blank" rel="ugc" href="https://runpod.io?ref=tbivgil2">Runpod</a> with help from the <a target="_blank" rel="ugc" href="https://www.youtube.com/watch?v=d49mCFZTHsg">Ostris Tutorial Here</a>.Suggested prompt for all uses: <code>Remove the white parts, use the image for context.</code>For Uncropping/Outpainting: The intended purpose is to take a cropped image, expand the canvas size higher than the actual image and fill it with white. Use that as Image 1.Use the image of the persons head as Image 2. I suggest an image of a head that cropped to a square. Maybe rotate it so it makes sense if it were transferred onto Image 1 directly.If the image quality or even backgrounds are too different between the two images you may need to add additional context like hair color, location, etc, but less details is better in my experience. If you'd like a more unified quality, I had success using this with this <a target="_blank" rel="ugc" href="https://civarchive.com/models/2046703/luisap-qwen-edit-upscaler-and-denoise-v3-fixed">Upscale LoRa.</a> You could try other colors but I have not tested with/trained on anything but white.For Inpainting: You can use photoshop or the white paint from the built in Comfyui Mask Editor, see the below example: <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/8263a08c-b8ce-48b6-bad0-6639834482c6/width=525/8263a08c-b8ce-48b6-bad0-6639834482c6.jpeg" />

UNCROP/INPAINT/OUTPAINT WITH CONTEXT IMAGE for F.2 Klein 9B + QWEN IMAGE EDIT LORA

Suggested tags: <code>remove the white parts, use the image for context</code>Suggested strength: 1.0Flux.2 Klein 9B is already very good at doing this without this LoRA. I was quite amazed when testing on/off how many results looked fine without the LoRA. This LoRA still has its use cases in my dataset creation workflow and I spent time and money on <a target="_blank" rel="ugc" href="https://runpod.io/?ref=tbivgil2">Runpod</a> making it so I'll still release it, but feel free to try it with/without. Also tested with colors besides white and it worked fine. My workflow is embedded in all the images again. Examples generated using <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.2-klein-9b-fp8/blob/main/flux-2-klein-9b-fp8.safetensors">flux-2-klein-9b-fp8.safetensors</a> and corresponding <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/vae-text-encorder-for-flux-klein-9b/resolve/main/split_files/text_encoders/qwen_3_8b_fp8mixed.safetensors">fp8 text encoder</a> at around 4-6 steps. Also Flux 2.Klein i2i <a target="_blank" rel="ugc" href="https://docs.bfl.ai/guides/prompting_guide_kontext_i2i">prompting guide</a> is helpful. If you are using 9b-base, in my workflow change sampler to euler and increase number of steps.

Files with SHA256: 3fe90629390454f4b18a6cbea8918e8e36223781996a78d35b4c18db8731e9db