Does an image's position and the batch size change which image I get for a given seed (ComfyUI and diffusers), and how do I regenerate one image from a batch on its own?

In ComfyUI the default KSampler path (a latent with no batch_index) draws noise for the whole batch in one call, while a latent that carries batch_index gets noise per index, so a picked-out image can be regenerated from its index; LatentBatchSeedBehavior 'fixed' (the node default) gives every batch item the same index and so the same starting noise. Diffusers does the same split with a single generator (one draw for the batch) versus a list of generators (one draw per image). Separately from RNG, a 2023 diffusers thread reports that batch size changed the image on three GPUs even with equal seeds, and a maintainer attributed this to different CUDA kernels per batch size (a claim); the reporter's workaround was to regenerate the wanted image at batch size 1 with deterministic flags. Curator correction 2026-10-23 (discovery audit record C3-B681-09; sources re-fetched 2026-10-23, excerpts re-located by curator GET): Problem. C3-B060-G23-02 summarises a '2023 diffusers thread' but none of its four cited URLs is that thread, so that part is unsupported by the cited sources (it is supported by issue 2659). Correction type: (d) plus (c). Method. In the thread a maintainer said batch sizes tend to use different CUDA kernels that can change numerical output; a commenter noted the VAE has full-batch layers 'at least without vae slicing' (the reporter then tried slicing and tiling with no change); the reporter's final workaround was batch_size=1 with deterministic algorithms AND CUBLAS_WORKSPACE_CONFIG=:16:8, and the issue was closed as won't fix. The candidate omits the CUBLAS setting and the VAE-batch hypothesis. Limitations. Anecdotal thread on diffusers 0.16-era and torch 2.0. Version and date. Fetched 2026-10-23. Curator qualifications: 2659 (opened 2023-03-13; 'generated images are slightly varying with batch size', RTX 3090, fp16): contributor kig: 'The batch size does effect the generated images, at least without vae slicing, since the vae has full-batch layers'; patrickvonplaten (CONTRIBUTOR): 'different batch sizes tend to use different kernels in CUDA which can lead to different numerical outputs'; reporter later needed torch.use_deterministic_algorithms(True) and CUBLAS_WORKSPACE_CONFIG=:16:8 under PyTorch 2.0; maintainer: 'I don't think we can do more than ... use_deterministic_algorithms(True)'. 6222: yiyixuxu 'I don't think it is a bug' (12-19) -> 'actually I think it might be a bug ... if we pass a list of generators, we should be able to reproduce any of the single image output' (12-20) -> cannot reproduce (12-28); patrickvonplaten 'Yes it's a bug' (12-26, 01-11) -> 'I don't think we have a bug' (01-17); then marked stale. Candidate's 'three GPUs' was not located in the comments read (not checked further). Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.

{
  "citations": [
    {
      "url": "https://github.com/Comfy-Org/ComfyUI",
      "note": "see C3R-0118 (sample.py, nodes_latent.py, nodes.py at 1a82e6d0); gh api -X GET repos/huggingface/diffusers/issues/2659 and /comments (2026-10-22; live JSON, not hashed); gh api -X GET repos/huggingface/diffusers/issues/6222/comments (2026-10-22; live JSON)"
    },
    {
      "url": "https://github.com/Comfy-Org/docs/blob/506a4a94db30524adb8706667aec050d71dbdf60/built-in-nodes/LatentBatchSeedBehavior.mdx",
      "note": "see C3R-0118 (sample.py, nodes_latent.py, nodes.py at 1a82e6d0); gh api -X GET repos/huggingface/diffusers/issues/2659 and /comments (2026-10-22; live JSON, not hashed); gh api -X GET repos/huggingface/diffusers/issues/6222/comments (2026-10-22; live JSON)"
    },
    {
      "url": "https://github.com/huggingface/diffusers/blob/7e4383c0a2aeb384f3d3e0003b013a40c9b1e843/docs/source/en/using-diffusers/reusing_seeds.md",
      "note": "see C3R-0118 (sample.py, nodes_latent.py, nodes.py at 1a82e6d0); gh api -X GET repos/huggingface/diffusers/issues/2659 and /comments (2026-10-22; live JSON, not hashed); gh api -X GET repos/huggingface/diffusers/issues/6222/comments (2026-10-22; live JSON)"
    },
    {
      "url": "https://github.com/huggingface/diffusers/issues/2659",
      "note": "see C3R-0118 (sample.py, nodes_latent.py, nodes.py at 1a82e6d0); gh api -X GET repos/huggingface/diffusers/issues/2659 and /comments (2026-10-22; live JSON, not hashed); gh api -X GET repos/huggingface/diffusers/issues/6222/comments (2026-10-22; live JSON)"
    },
    {
      "url": "https://github.com/huggingface/diffusers/issues/6222",
      "note": "see C3R-0118 (sample.py, nodes_latent.py, nodes.py at 1a82e6d0); gh api -X GET repos/huggingface/diffusers/issues/2659 and /comments (2026-10-22; live JSON, not hashed); gh api -X GET repos/huggingface/diffusers/issues/6222/comments (2026-10-22; live JSON)"
    },
    {
      "url": "https://api.github.com/repos/huggingface/diffusers/issues/2659/comments",
      "note": "correction source (record C3-B681-09): comment by patrickvonplaten, 2023-03-15; comment by kig, 2023-03-14; comment by vvsotnikov, 2023-05-22"
    }
  ]
}