Point at the public multimodalart/qwen3vl-conditioner, called without a token

README.md

@@ -18,7 +18,7 @@ audio references, at **bfloat16 with no quantization anywhere**.
 
 This Space is the denoising half of the `ref2va` task: the 61.73 GiB `transformer_ref` partition and the two
 autoencoders. The 62.14 GiB Qwen3-VL conditioner runs in
-[`minimax-h3-conditioner`](https://huggingface.co/spaces/diffusers-internal-dev/minimax-h3-conditioner), which this
+[`qwen3vl-conditioner`](https://huggingface.co/spaces/multimodalart/qwen3vl-conditioner), which this
 Space calls over the gradio API for every request — the same conditioner Space, and the same resident weights, that
 the keyframe half [`minimax-h3`](https://huggingface.co/spaces/diffusers-internal-dev/minimax-h3)
 uses.
@@ -31,7 +31,7 @@ fit unquantized:
 
 | Space | Subfolders | Download | Resident |
 |---|---|---|---|
-| [`minimax-h3-conditioner`](https://huggingface.co/spaces/diffusers-internal-dev/minimax-h3-conditioner) | `text_encoder/` + `tokenizer/` + `processor/` | 66.7 GB | 62.15 GiB bf16 |
+| [`qwen3vl-conditioner`](https://huggingface.co/spaces/multimodalart/qwen3vl-conditioner) | `text_encoder/` + `tokenizer/` + `processor/` | 66.7 GB | 62.15 GiB bf16 |
 | this one | `transformer_ref/` + `vae/` + `audio_vae/` | 77.3 GB | 61.73 GiB bf16 + 10.43 GiB float32 |
 
 ## References
@@ -168,7 +168,7 @@ on is cold and a cold one pays the lazy 72.16 GiB `PIPE.to("cuda")` inside its f
 
 | Variable | Default | Meaning |
 |---|---|---|
-| `H3_CONDITIONER` | `diffusers-internal-dev/minimax-h3-conditioner` | The Space this one asks for embeddings. |
+| `H3_CONDITIONER` | `multimodalart/qwen3vl-conditioner` | The public Space this one asks for embeddings; the client passes no token, so the call runs on the caller's own quota. |
 | `H3_AOTI` | `0` | `1` loads the compiled block package. |
 | `H3_PLACEMENT` | `lazy` | `lazy` moves all 72.16 GiB onto the card on the first GPU call and leaves it there; `offload` hands placement to `ComponentsManager.enable_auto_cpu_offload` instead. |
 | `H3_ATTENTION` | `_native_cudnn` | cuDNN's fused kernel, 10–20% faster than the SDPA default and needs nothing installed. flash-attention 3 is sm90-only and this pool is sm120. The two VAEs are pinned to torch SDPA instead: they are float32, which cuDNN has no kernel for. |
@@ -178,7 +178,7 @@ on is cold and a cold one pays the lazy 72.16 GiB `PIPE.to("cuda")` inside its f
 
 ## Required secret
 
-`HF_TOKEN` — `diffusers-internal-dev/MiniMax-H3` is private, and so is the conditioner Space this one calls.
+`HF_TOKEN` — `diffusers-internal-dev/MiniMax-H3` is private. The conditioner is a public Space and is called without a token, so that round trip runs on the caller's own quota rather than this org's.
 
 ## Where diffusers comes from