Link original Qwen model and finish naming updates

PROMPTING.md

@@ -1,4 +1,4 @@
-# Prompting Prism / Qwen Image 2.1
+# Prompting Qwen Image 2.1 NVFP4
 
 Start with a concrete natural-language paragraph: medium, subject, action,
 relationships, composition, lighting, materials, then exact lettering. Keep each

README.md

@@ -18,7 +18,7 @@ tags:
 
 # 🚀 Qwen Image 2.1 — NVFP4 for ComfyUI
 
-**This is an independent NVFP4 quantization of Qwen Image 2.1, created by the Qwen team.** The original model and architecture are Qwen's work. I converted the official [Comfy-Org/Qwen-Image-2.1 BF16 checkpoint package](https://huggingface.co/Comfy-Org/Qwen-Image-2.1) and packaged the quantized weights, workflows, and validation here. This is not a new base model or an official Qwen release.
+**This is an independent NVFP4 quantization of [Qwen Image 2.1](https://huggingface.co/Qwen/Qwen-Image-2.1). The Qwen team created the original model.** The original model and architecture are Qwen's work. I converted the official [Comfy-Org/Qwen-Image-2.1 BF16 checkpoint package](https://huggingface.co/Comfy-Org/Qwen-Image-2.1) and packaged the quantized weights, workflows, and validation here. This is not a new base model or an official Qwen release.
 
 **The image model AND the text encoder. 12.42 GB for the complete package.**
 

SHA256SUMS

@@ -98,14 +98,14 @@ fa6f566d4cf29b171bc996ad81857cf0dbdbb9cc5b8524297c1f1ca1738db99f  gallery.html
 936375ea3fb35c7c33dbe59c7090c35edf019e6119bc6b775f74f3d859b49a54  input/qwen_image_2.1_edit_reference.png
 06b7d356cd8cb6b79aa2eef3f934d1e1e8e1c2aa1e85dcc23915dd9a68197249  LICENSE
 0215c805cf5ee96af84731daffb90ba39942c33ef8159b897c754156ffbc95f6  NOTICE
-09a924579e9efea1ca3c3bccec2bf04ab6bd00dda6e1719a171f32a115aebcad  PROMPTING.md
-075a0e74648bc1bbd0dae2649244fec67801ba7407dc604057f11f5d915feb2c  README.md
+13a380a639c0e7a34c43f656ede817e179ea5e20e4b5a6b0a779c756fa3097db  PROMPTING.md
+d369c50eaf65a0fbe81c366930660544c153327802faabf89125af4d7b0ae0ae  README.md
 230184f60bae2feaf244f10a8bac053c8ff33a183bcc365b4d8b876d2b7f4809  runtime/LICENSE-GPL-3.0
 2c13ec9046ffa720484c569acce153f4759da47e9bc008af56d68d583854e2fa  runtime/qwen21-nvfp4-conditioning.patch
 787b656910e289283b0671311b479949b2496f9a233413fa71ce0f478866d9dc  runtime/README.md
 640b0140cb6cd3b93cfd4b7899f6bac48b0c596fc707e03c926fdc15aa57352e  text_encoders/qwen3vl_8b_nvfp4.manifest.json
 cdd9b85bcb60d5cb358ddecfd45a48fa15cb728b70d88bd2028840eaef095d16  text_encoders/qwen3vl_8b_nvfp4.safetensors
-f0a09696345c6fb96149f230ea095a5b77d31ebfeda24fcbab95ff3b6dc7e0c0  tools/convert.py
+2be2baabe8ae36585bada5c4ae33c7c73425940773ba42060c96247b0e778437  tools/convert.py
 22f7cf73b46589cea8f8c78169f0f7c6a3a4c8ce98957ef9ab7cfdd6929e37ad  tools/run_workflow.py
 b99db3f33715e108ba69180b6afd61d237b4f588e5cb2af34c1a8cbe5e1285e5  tools/verify.py
 bb21f7473051e1ac368515dd3f2e15cd44d7a11748ee8823e1ddca3e4876b7c9  vae/qwen_image_2.1_vae_bf16.safetensors

tools/convert.py

@@ -63,7 +63,7 @@ def main():
     expected = 192 if args.component == "dit" else 252
     if count != expected:
         raise ValueError(f"Recipe matched {count} matrices, expected {expected}")
-    metadata.update(format="pt", conversion="Prism native NVFP4; protected tensors unchanged; Built with Qwen")
+    metadata.update(format="pt", conversion="Qwen Image 2.1 native NVFP4; protected tensors unchanged; Built with Qwen")
     args.output.parent.mkdir(parents=True, exist_ok=True)
     save_file(output, str(args.output), metadata=metadata)
     report = {"source": args.source.name, "source_sha256": digest(args.source), "output": args.output.name,