ABC Young Performers Awards semi-final. Tom Lowe, alto saxophone, and Coady Green, piano, play: Ned ROREM: Picnic on the Marne. Erwin SCHULHOFF: Hot Sonata. John CARMICHAEL: Latin American Dances.…

ABC Young Performers Awards semi-final. Tom Lowe, alto saxophone, and Coady Green, piano, play: Ned ROREM: Picnic on the Marne. Erwin SCHULHOFF: Hot Sonata. John CARMICHAEL: Latin American Dances.…

ABC Young Performers Awards semi-final. Tom Lowe, alto saxophone, and Coady Green, piano, play: Ned ROREM: Picnic on the Marne. Erwin SCHULHOFF: Hot Sonata. John CARMICHAEL: Latin American Dances.…

Hi John, Thank you for the detailed breakdown and the suggestions of LaMa, RORem, and OSOR. I’ve spent the last few days benchmarking these against my specific use case, and I wanted to share the results, as they highlight a significant gap in performance for high-end virtual staging. **The Current Workflow:** I am using a fine-tuned **RF-DETR Seg Large** model to generate the initial furniture masks. To ensure we capture shadows and contact edges, I apply a **20px dilation** before feeding the mask to the inpainting models. **The Results:** 1. **LaMa:** As you noted, it is a great “cheap” eraser, but for “defurnishing” (removing large items like beds/sofas), it fails semantically. It essentially “smudges” the surrounding colors into the hole. It creates a blurry, greyish-red “cloud” where the bed was, rather than reconstructing the hidden floor grain or wall texture. It lacks the “imagination” required for architectural reconstruction. 2. **RORem:** While RORem is built on SDXL and is much faster than Qwen, the results have been disappointing in terms of **Texture Integrity and Blending**. I am seeing significant “texture melting” (as seen in the attached output). The floor patterns become warped/liquid, and the transition between the original pixels and the AI-generated pixels is very jarring, even with feathered masks. I used: pipe = AutoPipelineForInpainting.from_pretrained( “LetsThink/RORem”, torch_dtype=torch.float16, variant=None).to(“cuda”) 3. **The Qwen Comparison:** Honestly, **Qwen-Image-Edit** remains the gold standard in my tests. Even though it is VRAM-heavy and slow, it is the only model that actually “understands” the instruction to reveal the architectural shell. It reconstructs the hardwood floor lines and wall textures with a level of logic that the others haven’t matched. **Visual Evidence (Attached):** * **Image 1:** Original Photo (Furnished) * **Image 2:** My RF-DETR + Dilated Mask (The input provided to models) * **Image 3:** RORem Output (Showing the “melting” floor and poor blending) **My Concern:** We are aiming for a commercial-grade product where we need to meet strict metrics (SSIM ≥≥ 0.95 and EdgeMAD ≤≤ 2px). While Qwen hits the visual quality, the latency is the blocker. However, RORem and LaMa seem to fail the visual “realism” test entirely for large-scale removal. Do you have any suggestions on how to stabilize the geometry in RORem (perhaps via ControlNet-MLSD or Depth)? Or is there a lighter “instruction-based” model that behaves more like Qwen but with the speed of SDXL? Looking forward to your thoughts! * * *

There are lighter alternatives to Qwen-Image-Edit, but after trying them, it looks like each has its own quirks: * * * Yes — for this particular job I would probably **not** start by trying to squeeze Qwen-Image-Edit into less VRAM. For masked object removal / room emptying, I would try the following order instead: 1. **LaMa** as the cheap/default eraser. 2. **RORem** when LaMa is too conservative or leaves an implausible hole. 3. **OSOR** when the object has shadows/reflections or the supplied mask does not cover all of the object’s visible effects. 4. If you have **depth / normals / a mesh / multiple views** , treat that as a separate structural-reconstruction problem and use those signals to guide inpainting rather than asking an RGB-only model to guess everything. The important distinction is that _removing an object_ and _emptying a furnished room_ gradually become two different problems. For a chair in front of a wall, an inpainting model can often infer a plausible continuation of the wall. For a large cabinet hiding the wall/floor boundary, there may simply be no RGB evidence for the true geometry behind it. At that point the model is generating a **plausible completion** , not recovering hidden ground truth. So my default practical pipeline would be: mask ↓ exact mask + slightly expanded-mask variant ↓ LaMa ↓ if too conservative / poor semantic completion RORem ↓ if shadow/reflection/residual footprint is the problem OSOR ↓ keep the least-invasive successful result I would test the mask before spending much time changing models. A very cheap A/B test is: A: exact object mask B: object mask + small dilation Furniture often leaves contact shadows, anti-aliased edges, reflected color, etc. outside the segmentation mask. On the other hand, making the mask _too_ large gives a generative model more freedom to redesign the room, so I would not blindly use one large dilation value for every image. Why these three would be my main candidates (click for more details) Why SDXL inpainting can generate another object instead of an empty background (click for more details) Room emptying is eventually a geometry problem, not just an inpainting problem (click for more details) About ControlNet: useful, but I would not treat it as the lightweight replacement by itself (click for more details) A few cheap things I would test before adding another model (click for more details) VRAM reduction if you still want an SDXL / Diffusers route (click for more details) My practical decision tree (click for more details) License / deployment note (click for more details) So, for your exact description — **indoor photo + mask + modest VRAM + “erase this, don’t replace it with another random object”** — my first three tests would simply be: 1. LaMa 2. RORem 3. OSOR-SDXL only for cases where shadows/reflections/incomplete masks are the hard part and I would compare the **exact mask against one slightly expanded mask** before adding more models. If LaMa works, it is probably the nicest operational answer because it is so lightweight. If it is too conservative, RORem looks like the most directly targeted next step. If even that fails because a large piece of furniture has hidden the actual room geometry, I would stop treating that failure as “find a better eraser” and move the structural information — depth/layout/multiview/mesh if available — into a separate guidance stage.

YouTube video by Julius Katchen - Topic

Cupboard Love Music: Madeline Dring Libretto: DF Aitken   Three Sisters Who Are Not Sisters Music: Ned Rorem Libretto: Gertrude Stein   Director: Jonny Danciger  As so often, the Grimeborn Opera Festi...