基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
언어부터 이미지, 오픈 웨이트부터 API까지. 기능과 실제 비용을 비교하세요.
다음 아이디어에 맞는 AI를 찾아보세요.
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
GGUF quantizations of pottokao/LFM2.5-24B-A2B-Uncensored (LiquidAI LFM2.5-24B-A2B decensored with Heretic ARA, searched and tested with thinking enabled; see the main repo for results). KV cache is small (only 10 of 40 layers are attention, ~20 KB per token in F16), so most of the VRAM goes to weights. The model always thinks before answering; allow a generous output budget. Liquid AI's official DSpark draft targets the original weights (acceptance on this model not yet measured).
번역 대기 중 · 원문 표시
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
> ⚠️ **Not a general-purpose LLM.** These files are the **text encoder of MiniMax-H3** and nothing else: cut to the > 50 layers H3 uses, with **no LM head** — they cannot chat or generate text. They exist so H3's 32B encoder fits a > **16 GB GPU in ComfyUI**. Built from the **official** MiniMax-H3 encoder (`MiniMaxAI/MiniMax-H3` → `text_encoder/`, revision `42ed227e`; Qwen3-VL-32B). Not abliterated. For comparison, on the same test: the earlier `MiniMax-H3-TextEncoder-Qwen3VL-32B-abliterated-GGUF` Q3_K_S (11.46 GB text part) scores 14.4% / 14.7%, and a stock llama.cpp Q3_K_S of the official weights 11.8% / 12.0%.
번역 대기 중 · 원문 표시
> 🆕 **Newer, better-quality build:** pottokao/MiniMax-H3-TextEncoder-16GB-GGUF — official encoder weights, quantized per tensor by how much each one affects the H3 DiT, K-quants only. At the same 12.65 GB `_vis` size its conditioning error is about half of this Q3_K_S (7.9% vs 14.4%), with 13.7 / 14.8 GB options at 6.4% / 4.9%. > ⚠️ The `_vis` file here stores the visual tower's 5-D `patch_embed` weight as-is; recent `gguf` versions refuse tensors with more than 4 dimensions, so it may fail to load on an up-to-date ComfyUI-GGUF. The new repo stores it the ComfyUI-GGUF way. > 🆕 有新版:pottokao/MiniMax-H3-TextEncoder-16GB-GGUF(官方權重、依 H3 DiT 敏感度逐張量量化、只用 K 系列)。同樣 12.65 GB 誤差約為這顆的一半。這裡的 `_vis` 檔在新版 gguf 套件上可能載不進去。 > 📌 Heads-up: I've been focused on still-image work lately, so I don't have the bandwidth to help with video setups like MiniMax-H3 for now. The files stay up as they are — thanks for understanding! > 最近重心放在平面攝影,影片類(像 MiniMax-H3)暫時比較沒辦法協助排錯。檔案會照舊留著,謝謝體諒! GGUF (llama.cpp) builds of the **MiniMax-H3 text encoder** — abliterated Qwen3-VL-32B, 50 layers, **Q3_K_S** (≈3.53 BPW).
번역 대기 중 · 원문 표시
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
One file does two jobs: it **rewrites** a short idea into a full MOSS-Image caption, then **encodes** that caption for the DiT. Weights are loaded once. A Q4-class file fits an 8 GB card. The quantization is **DHQ** (DiT-aware quantization): every tensor's format is chosen from measured damage on two rulers at once — the error after MOSS-Image's own text stage (what the DiT sees) and the KL of the rewrite — instead of llama.cpp's fixed per-type rules. At the same file size, every DHQ build beats the standard llama.cpp quant on both rulers. Use the **Dual-Head Dragon** ComfyUI node: **https://github.com/pottokao-dotcom/ComfyUI-DualHead-Dragon** (MOSS-Image support: `products/moss.py`).
번역 대기 중 · 원문 표시
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
> **Not affiliated with, or endorsed by, Alibaba / Qwen.** Quantized redistribution of the > `Qwen/Qwen-Image-2.1` diffusion transformer under the > **Qwen Research License** (copy included as `LICENSE`). **Non-commercial use only.** > [!IMPORTANT] > **Loads in stock city96/ComfyUI-GGUF — no patch, no extra nodes.** > These files carry `general.architecture = qwen_image`, so `UnetLoaderGGUF` recognises them directly > (GGUFs without that field fail with `Unknown model architecture!`). > > **Text encoder:** our Qwen-Image-2.1 Text Encoder GGUF > works with this DiT, but it needs one extra node first — > ComfyUI-GGUF-Qwen3VL-TE (stock ComfyUI-GGUF > doesn't load Qwen3-VL text encoders yet). With a **safetensors** text encoder (bf16 / int8 / FP8 from the same > repo family) nothing extra is needed. The sample / showcase images in this repo were generated with the technique behind **ComfyUI-QwenImage-PhotoStyles** — a small ComfyUI node (17 photographic styles; one short prompt becomes a full styled prompt via the PE-T2I rewriter). If you're interested in how the images are made, the node and its recipe are there.
번역 대기 중 · 원문 표시
> **Not affiliated with, or endorsed by, Alibaba / Qwen.** Community derivative of > `Qwen/Qwen-Image-2.1-PE-I2I`, > redistributed under the **Qwen Research License** (copy included as `LICENSE`, per §3.a). > **Non-commercial use only** (§1.i / §2.a); commercial use needs a separate licence from Qwen. The **image-editing prompt rewriter** for Qwen-Image-2.1 — a fine-tuned Qwen3.5-VL 9B that takes a vague editing instruction plus one or more input images and rewrites it into a precise, actionable editing prompt — with refusal behaviour reduced via Heretic directional ablation. This repo is the **llama.cpp build** and is **fully multimodal** — it ships both the language model GGUF and the vision projector, so it works for **text-only and image+text** editing.
번역 대기 중 · 원문 표시
> **Not affiliated with, or endorsed by, Alibaba / Qwen.** Community derivative of > `Qwen/Qwen-Image-2.1-PE-T2I`, > redistributed under the **Qwen Research License** (copy included as `LICENSE`, per §3.a). > **Non-commercial use only**; commercial use needs a separate licence from Qwen. **Q4_K_M** build of `pottokao/Qwen-Image-2.1-PE-T2I-Heretic` — the Qwen-Image-2.1 **prompt rewriter** with refusal behaviour removed (3/100 refusals @ KL 0.036, from 98/100 — best of a 1,600-trial search; dominates the earlier 7/100 @ 0.039, tag `v1-trial384`). > **`system_prompt.txt` is included and the model is useless without it.** That 10 KB > document *is* the output contract — structure, register, length, and the JSON shape. > Load it as the system message.
번역 대기 중 · 원문 표시
> 🍱 **All-GGUF Qwen-Image-2.1:** text encoder GGUF + DiT GGUF (Q8_0 / Q6_K / Q4_K_M, loads in stock ComfyUI-GGUF) + PE-T2I GGUF. > [!IMPORTANT] > **The 4 `model-0000x-of-00004` shards are the HF `transformers` checkpoint (bf16) — they do not load in ComfyUI.** > ComfyUI text encoders use a different key layout (the `model.language_model.` prefix is dropped > when repacking), so pointing ComfyUI at these shards will not work. > > For ComfyUI use one of these instead — all keep the vision tower, which 2.1 needs for editing. > **Mac / non-CUDA:** use the single file `qwen3vl_8b_bf16_heretic.safetensors` in *this* repo (full bf16, 17.5 GB — also in the GGUF repo) — > put it in `models/text_encoders/` and load it with the stock `CLIPLoader`, type `qwen_image`, then `TextEncodeQwenImage21`. > It is the only format here that needs no CUDA-specific kernels. > > | Repo | File | Loader | > |---|---|---| > | **this repo** | `qwen3vl_8b_bf16_heretic.safetensors` (bf16 single file, any device) | `CLIPLoader`, type `qwen_image` | > | `…-NVFP4` | `qwen3vl_8b_nvfp4_heretic.safetensors` | `CLIPLoader`, type `qwen_image` | > | `…-W4A8` | `qwen3vl_8b_w4a8_heretic.safetensors` | `CLIPLoader`, type `qwen_image` | > | `…-GGUF` | `qwen3vl_8b_heretic-Q4_K_M.gguf` + `mmproj-…-f16.gguf` | `CLIPLoaderGGUF` + the ComfyUI-GGUF-Qwen3VL-TE add-on node (without it: `[1, 512, 12288]` shape error) | > > You also need a ComfyUI new enough to know `QwenImage21`: **0.34.2 does not, 0.36.0 does.** > If `TextEncodeQwenImage21` is missing from your node list, that is why. > > Use *this* repo for `transformers` / diffusers / vLLM, or as the base for your own quantization. > **Not affiliated with, or endorsed by, Alibaba / Qwen.** Community derivative > (refusal-ablated) of `Qwen/Qwen3-VL-8B-Instruct` > — the model Qwen-Image-2.1 uses, unmodified, as its text encoder. Qwen releases that > model under **Apache-2.0**, so this derivative is redistributed under Apache-2.0 > (see `LICENSE` and `NOTICE`).
번역 대기 중 · 원문 표시
**DHQ = Dual-Head Quant.** Same heretic weights as Qwen-Image-2.1-Text-Encoder-Heretic-GGUF, quantized a different way: instead of llama.cpp's fixed rules, every tensor gets the precision that matters to **what the Qwen-Image-2.1 DiT actually reads** (measured per tensor with gradients through the DiT's text input), plus an importance matrix weighted the same way. Each file is **exactly the size of the standard llama.cpp file of the same name**, and better at every level. Tuned for **Qwen-Image-2.1 only**. Other models that use Qwen3-VL-8B (Ideogram 4, Boogu, JoyImageEdit) can load these files, but they were not tuned for them. Need Q5/Q6/Q8? Use the standard files in the GGUF repo — at those sizes the standard recipe is already as good. DHQ files are quantized **for use as a diffusion model's text encoder**: each tensor's precision is chosen by how much its quantization error changes what the target DiT reads (measured through the DiT's own text-input stage), not by next-token loss. They stay normal LLM GGUFs, so the same file can still write or rewrite prompts: where a model is also used as a prompt enhancer (Z-Image-Engineer-V6, the heretic Qwen3-VL-8B), every file is also checked for that (the PE column) and the tables show where it gets worse.
번역 대기 중 · 원문 표시
> [!IMPORTANT] > **Got `got input of size [1, 512, 12288]` with the GGUF? It's fixed.** > The GGUF files were fine all along — ComfyUI-GGUF just didn't load the Qwen3-VL vision tower. > Install the add-on node **ComfyUI-GGUF-Qwen3VL-TE**, > make sure the `mmproj` file sits next to the GGUF, restart ComfyUI. No need to re-download anything. > The same patch also fixes `Unknown model architecture!` for Qwen-Image-2.1 **DiT** GGUFs — so the whole > pipeline can run on GGUF. The sample / showcase images in this repo were generated with the technique behind **ComfyUI-QwenImage-PhotoStyles** — a small ComfyUI node (17 photographic styles; one short prompt becomes a full styled prompt via the PE-T2I rewriter). If you're interested in how the images are made, the node and its recipe are there. All three are in **this repo**. Every loader uses **type `qwen_image`** and feeds `TextEncodeQwenImage21`.
번역 대기 중 · 원문 표시
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
제공사, 분류, 입출력 조건을 조정하세요. 새 모델이 계속 등록됩니다.
월간 토큰 사용량으로 예상 API 비용을 비교하세요.
수집된 백만 토큰당 USD 요금입니다. 캐시 할인, 구간 요금, 추가 추론 출력, 세금은 제외됩니다. 최신 요금은 출처에서 확인하세요.
입력, 출력, 캐시 요금을 구분하고 동일 작업량으로 비교하세요. 이미지, 음성, 영상은 개수, 시간, 해상도로 과금될 수 있습니다.
반드시 그렇지는 않습니다. 버전별 라이선스, 상업 이용 제한, 정책을 확인하세요. 자체 호스팅에는 연산 및 유지 비용도 듭니다.
순위는 작업, 버전, 평가 방식에 따라 다릅니다. 실제 업무로 정확도, 지연, 안정성, 비용을 비교하세요.