YiSM-blossom5.1-34B-SLERP
CombinHorizon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。
From language to images, open weights to APIs. Understand capabilities and compare real costs.
Find the right engine for your next idea.
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。
The repository contains a fuller-NVFP4 weight profile of Qwen/Qwen3.8-27B in the native NInfer `.ninfer` artifact format, with the z-lab/Qwen3.8-27B-DFlash2 block-diffusion speculative drafter embedded in the same image. It runs on NInfer **v3** engines — Text and MTP components through format/shape routes the upstream runtime already implements, the optional NVFP4-encoded DFlash2 companion through the fork's runtime support. It is not a Transformers checkpoint, Safetensors distribution, or GGUF file. Compared with the official `nvfp4` profile it extends NVFP4 from the layers 0–55 MLP to nearly the whole Text backbone: - every Text `mlp/gate_up` and `mlp/down` is NVFP4 (the layers 0–55 words are copied bit-exactly from unsloth/Qwen3.8-27B-NVFP4; layers 56–63 are quantized locally from the official BF16 checkpoint); - every GDN `query_key_value_z` is NVFP4, and GDN `output` is NVFP4 on 47 of 48 layers; - full-attention `query_key_gate_value` is NVFP4 on the ten deepest layers and `attention/output` on 14/16, with 9 BF16 exception parents retaining the registered Qwen3.6-27B NVFP4 exception pattern; - the token embedding and full output head use groupwise W8G32_F16S instead of row-scaled FP8. This yields 247 NVFP4 parents with 247 site-level input divisors. Locally quantized parents use the documented encoder profile `NVFP4_MAXABS_DIVISOR_RNE_V1` (per-tensor FP32 divisor, per-16 E4M3FN block scales, RNE E2M1 codes) with site divisors calibrated by streaming the official BF16 checkpoint. The complete contract, encoder, calibration corpus, and validation evidence are `docs/maintainer/qwen3.8-27b-artifact.md` §14 in the fork.
The repository contains a QAT-sourced NVFP4 weight profile of Qwen/Qwen3.8-27B in the native NInfer `.ninfer` artifact format, with the z-lab/Qwen3.8-27B-DFlash2 block-diffusion speculative drafter embedded in the same image. It runs on NInfer **v3** engines — Text and MTP components through format/shape routes the upstream runtime already implements, the optional NVFP4-encoded DFlash2 companion through the fork's runtime support. It is not a Transformers checkpoint, Safetensors distribution, or GGUF file. This is a fourth weight profile for the existing `qwen3_8_27b` target — a peer of the official `groupwise-int` and `nvfp4` profiles and of the fork's fuller-requant `nvfp4full` profile. The Text weight stack is copied **word-for-word** from QUASAR-QAT/Qwen3.8-27B-QUASAR-NVFP4 — a quantization-aware-trained checkpoint (QUASAR loss-aware NVFP4 distillation against the frozen BF16 teacher, arXiv 2608.13966): - every one of the 496 text linear layers is NVFP4 (W4A4) — attention, gated-delta-net, and MLP alike, with no high-precision exceptions; - the QAT factory quantizes per site, so every constituent tensor of a fused parent shares one weight and input global scale; the converter enforces that sharing before copying a word, and the site input divisors ride the artifact directly; - the GDN control projections are decoded from their QAT NVFP4 words to the BF16 control parent the engine consumes.
See https://comfyanonymous.github.io/ComfyUI_examples/audio/ or https://docs.comfy.org/tutorials/audio/ace-step/ace-step-v1 for how to use it in ComfyUI. ACE Step v1 M2M Editing ACE-Step v1 Text to Instrumentals Music ACE Step v1 Text to Song
These are repackaged files to work with ComfyUI, original model repo is: https://huggingface.co/ACE-Step/Ace-Step1.5 ACE-Step 1.5XL Turbo: Text to Music ACE-Step 1.5XL SFT: Text to Music ACE-Step 1.5 Music Generation AIO ACE-Step 1.5XL Base: Text to Music ACE-Step 1.5 Music Generation Workflow ACE-Step 1.5 AI Lyric Song Generation ACE-Step 1.5 Music Generation (4B LLM )
Anima Lllite: Any Control to Image Before After Anima Lllite: Depth Control to Image Before After Anima Lllite: Image Inpainting Before After
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。
- https://huggingface.co/ZhengPeng7/BiRefNet - https://huggingface.co/egeorcun/lucida
Boogu image 0.1 Edit Int8 Before After Boogu image 0.1 Edit Before After Boogu Turbo: Text to Image
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。
Original model repository: - https://huggingface.co/lodestones/Chroma1-HD - https://huggingface.co/silveroxides/Chroma1-HD-fp8-scaled - Chroma1-HD.safetensors by lodestones - Chroma1-HD-fp8mixed.safetensors by silveroxides
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。
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。
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。
- https://github.com/ByteDance-Seed/Depth-Anything-3 - https://huggingface.co/depth-anything/DA3-BASE - https://huggingface.co/depth-anything/DA3METRIC-LARGE - https://huggingface.co/depth-anything/DA3MONO-LARGE - https://huggingface.co/depth-anything/DA3-SMALL Depth Map: Depth Anything 3 Before After Depth Estimation: Depth Anything 3 Before After
- https://huggingface.co/baidu/ERNIE-Image - https://huggingface.co/baidu/ERNIE-Image-Turbo
- https://huggingface.co/briaai/Fibo-2.0-dev - https://huggingface.co/briaai/Fibo-2.0-edit-turbo The model weights are © BRIA AI and licensed under Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0). You may use them for non-commercial purposes only. Commercial use requires a separate agreement with BRIA AI: https://platform.bria.ai/licensing/pricing?model=fibo-2 The weights are provided as is, without warranties of any kind. See Section 5 of the license (Disclaimer of Warranties and Limitation of Liability).
This is a smaller checkpoint for flux1-dev that will work better for ComfyUI users with less VRAM (under 24gb). Flux.1 Inpaint Before After Flux.1 Dev USO Reference Image Generation Before After Flux.1 Outpaint Before After Flux.1 Dev fp8: Text to Image Flux.1 Dev: Text to Image Flux.1 Canny Model Before After Flux.1 Depth Lora Before After Flux.1 Redux Model
Original model repository: https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev https://comfyanonymous.github.io/ComfyUI_examples/flux/#flux-kontext-image-editing-model
Original model repository: https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev All diffusion model files in this repo are licensed the same as the ones in the original repo: https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev The files in this repo are best used with ComfyUI using the Flux examples.
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。
Original model repository: https://huggingface.co/black-forest-labs/FLUX.1-schnell This flux1-schnell model has weights in FP8, which makes running in ComfyUI much faster and use less memory.
These are quantized weights. The original FLUX.2 repo is here: FLUX.2-dev. - Flux2TurboComfyv2.safetensors by ByteZSzn - Flux_2-Turbo-LoRA_comfyui.safetensors by ByteZSzn Flux.2 Dev Before After Flux.2 Dev Text to Image Product Mockup(Flux.2 Dev FP8)
- https://huggingface.co/black-forest-labs/FLUX.2-klein-4B - https://huggingface.co/black-forest-labs/FLUX.2-klein-base-4B
Adjust provider, category or input/output filters. New models are added continuously.
Adjust monthly token usage to compare estimated API costs.
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.