SAVRN
Search Contact SAVRN

Open-weight model · Text to image

Ruach_Studio_Models_v2

by Viktor Zhuromskyy goldhub/Ruach_Studio_Models_v2

Ruach_Studio_Models_v2 is an open-weight model for text to image from Viktor Zhuromskyy, released under other. Its published files total 239.9 GB. It draws 780 downloads a month.

Everything Ruach Studio runs on, in one place and laid out as its own folders: the music model and its decoders, the transcriber, the sliders, the stems' and the sound upscaler's models, Whisper, the style listener, the studio's own adapters, and the Artist's…

Parameters—
Context—
Weights239.6 GB
Licenseother
AccessOpen weights
Monthly Downloads780

Model Card

Everything Ruach Studio runs on, in one place and laid out as its own folders: the music model and its decoders, the transcriber, the sliders, the stems' and the sound upscaler's models, Whisper, the style listener, the studio's own adapters, and the Artist's painters with the adapters their authors let be shared. 152 files, 240 GB. A copy of the studio's own disk, file for file: what lies here is what it paints and sings with. It takes the place of goldhub/RuachStudioModels, which goes after 17 October 2026. Nothing here is ours but the conversions and the studio's own adapters. Every other file is its authors' work, unchanged, under its authors' licence, credited below and line by line in…

Excerpt from the card by Viktor Zhuromskyy, licensed other.

Identity and Version

Repository
goldhub/Ruach_Studio_Models_v2
Publisher
Viktor Zhuromskyy
Task
Text to image
Modality
Image
Library
ggml
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
ca8a1e2f5bbad7206b8336f875ba8ad132e06eee
First published
2026-10-10
Last updated
2026-10-15

Files and Weights

157 files, 239.9 GB in total. The weights are 83 files totalling 239.6 GB in bin, gguf, safetensors.

Weights83 files · 239.6 GB
Configuration34 files · 1.3 MB
Tokenizer12 files · 39.3 MB
Documentation15 files · 120.4 KB
Other11 files · 340.0 MB
Repository2 files · 6.4 KB
Every file
FileTypeSizeSHA-256
artwork/Qwen-Image-2.1/text_encoder/model-00001-of-00004.safetensorsWeights5.0 GB dde00291b5f7
artwork/Qwen-Image-2.1/text_encoder/model-00002-of-00004.safetensorsWeights4.9 GB 9047faccc0a6
artwork/Qwen-Image-2.1/text_encoder/model-00003-of-00004.safetensorsWeights4.9 GB 8c54187654c0
artwork/Qwen-Image-2.1/text_encoder/model-00004-of-00004.safetensorsWeights2.7 GB 5311532aaaea
artwork/Qwen-Image-2.1/transformer/diffusion_pytorch_model-00001-of-00002.safetensorsWeights10.0 GB 9e6bc2d641e6
artwork/Qwen-Image-2.1/transformer/diffusion_pytorch_model-00002-of-00002.safetensorsWeights4.3 GB 3aaf234dcbe1
artwork/Qwen-Image-2.1/vae/diffusion_pytorch_model.safetensorsWeights1.4 GB a07a1b7c4ee2
artwork/Qwen-Image-2512/checkpoints/BASE QW2512 fp8_e4m3fn.safetensorsWeights20.4 GB 5dc80554d5d8
artwork/Qwen-Image-2512/checkpoints/IntoRealism QW2512 v1 fp8.safetensorsWeights20.4 GB b7f5d703b5a3
artwork/Qwen-Image-2512/checkpoints/JibMix QW2512 v6 fp8.safetensorsWeights20.4 GB 45ab8add7e97
artwork/Qwen-Image-2512/checkpoints/Real QW2512 v2 fp8.safetensorsWeights20.4 GB b57c00a8d4c6
artwork/Qwen-Image-2512/gguf/qwen-image-2512-Q4_K_M.ggufWeights13.2 GB b2a5f6249eb5
artwork/Qwen-Image-2512/gguf/qwen-image-2512-Q6_K.ggufWeights16.8 GB 58c7fcea3d29
artwork/Qwen-Image-2512/lightning/Qwen-Image-2512-Lightning-8steps-V1.0-bf16.safetensorsWeights849.6 MB b48fb1a8edd9
artwork/Qwen-Image-2512/text_encoder/model-00001-of-00004.safetensorsWeights5.0 GB d725335e4ea2
artwork/Qwen-Image-2512/text_encoder/model-00002-of-00004.safetensorsWeights5.0 GB b1830db6908d
artwork/Qwen-Image-2512/text_encoder/model-00003-of-00004.safetensorsWeights4.9 GB 09c1807c6d00
artwork/Qwen-Image-2512/text_encoder/model-00004-of-00004.safetensorsWeights1.7 GB 5dd068336d14
artwork/Qwen-Image-2512/vae/diffusion_pytorch_model.safetensorsWeights253.8 MB 0c8bc8b758c6
artwork/Qwen3-4B-Instruct-2507/model-00001-of-00003.safetensorsWeights4.0 GB 75311d91bb08
artwork/Qwen3-4B-Instruct-2507/model-00002-of-00003.safetensorsWeights4.0 GB 0b48adbb1f60
artwork/Qwen3-4B-Instruct-2507/model-00003-of-00003.safetensorsWeights99.6 MB 7dd39ccca5e4
artwork/loras/qwen-image-2.1/Fantasy ArtStyle v1.safetensorsWeights293.7 MB d8ed904e65ec
artwork/loras/qwen-image-2.1/Frank Frazetta.safetensorsWeights872.5 MB 874fbe8a1ded
artwork/loras/qwen-image-2.1/GPT-Image-2 Anime.safetensorsWeights83.9 MB 8f43f3d2f30d
artwork/loras/qwen-image-2.1/Lenovo UltraReal.safetensorsWeights79.7 MB 7f1e95c3ec1e
artwork/loras/qwen-image-2512/Film Photography v1.safetensorsWeights147.7 MB 92124455ff64
artwork/loras/qwen-image-2512/PHOTOSTYLE BY SEAN ARCHER - SFW v2.safetensorsWeights590.1 MB 1be6b336f939
artwork/loras/qwen-image-2512/QWEN-2512-Lightning-4steps-V1.0-bf16.safetensorsWeights849.6 MB de0d236e54ec
artwork/loras/qwen-image-2512/QWEN-2512-Lightning-4steps-V1.0-fp32.safetensorsWeights1.7 GB ad12117461cb
artwork/loras/qwen-image-2512/QWEN-2512-Lightning-8steps-V1.0-fp32.safetensorsWeights1.7 GB 4f98e2820339
artwork/nsfw-filter/model.safetensorsWeights343.2 MB 97b2ce64ec14
listener/Qwen2.5-Omni-7B-GGUF/Qwen2.5-Omni-7B-Q3_K_M.ggufWeights3.8 GB 595f064b4456
listener/Qwen2.5-Omni-7B-GGUF/Qwen2.5-Omni-7B-Q4_K_M.ggufWeights4.7 GB 09883dff531d
listener/Qwen2.5-Omni-7B-GGUF/Qwen2.5-Omni-7B-Q5_K_M.ggufWeights5.4 GB 2b9e2b61d323
listener/Qwen2.5-Omni-7B-GGUF/Qwen2.5-Omni-7B-Q6_K.ggufWeights6.3 GB 23cc198c9f72
listener/Qwen2.5-Omni-7B-GGUF/Qwen2.5-Omni-7B-Q8_0.ggufWeights8.1 GB 2cb12eb661bc
listener/Qwen2.5-Omni-7B-GGUF/Qwen2.5-Omni-7B-UD-Q2_K_XL.ggufWeights3.2 GB 9ef3697f85a8
listener/Qwen2.5-Omni-7B-GGUF/mmproj-Qwen2.5-Omni-7B-Q8_0.ggufWeights1.5 GB 858f1ff0dab2
listener/Qwen2.5-Omni-7B-GGUF/mmproj-Qwen2.5-Omni-7B-f16.ggufWeights2.6 GB 7ed062b35f15
loras/YuE2-instrumental-cot-full-loras/ar_lora_inst_v3abc.safetensorsWeights279.0 MB 2252d7071fbf
loras/duduk-yt-r16/duduk-yt-r16-e080.safetensorsWeights58.8 MB 50d57fa17b6d
loras/duduk-yt-r16/duduk-yt-r16-e140.safetensorsWeights58.8 MB bd774670dae5
loras/duduk-yt-r16/duduk-yt-r16-e160.safetensorsWeights58.8 MB 148e70e0c0f2
loras/duduk-yt-r16/duduk-yt-r16-e180.safetensorsWeights58.8 MB 8610d557e75b
loras/duduk-yt-r16/duduk-yt-r16-e200.safetensorsWeights58.8 MB 852409ff7ae8
loras/shofar-yt-r16/shofar-yt-r16-e099.safetensorsWeights58.8 MB 038e5db622d3
loras/shofar-yt-r16/shofar-yt-r16-e110.safetensorsWeights58.8 MB a4a4d15e5417
loras/shofar-yt-r16/shofar-yt-r16-e121.safetensorsWeights58.8 MB f5b1cd33330c
loras/shofar-yt-r16/shofar-yt-r16-e167.safetensorsWeights58.8 MB daf0cc3a41a8
loras/voice-ru-f-contralto-154/voice-ru-f-contralto-154-e026.safetensorsWeights58.8 MB 6baf6ec96f3f
loras/voice-ru-f-contralto-167/voice-ru-f-contralto-167-e029.safetensorsWeights58.8 MB f17086d2d648
loras/voice-ru-f-contralto-171/voice-ru-f-contralto-171-e029.safetensorsWeights58.8 MB e3ba8a2b981e
loras/voice-ru-m-baritenor-117/voice-ru-m-baritenor-117-e029.safetensorsWeights58.8 MB a3e249d894c9
loras/voice-ru-m-baritenor-127/voice-ru-m-baritenor-127-e026.safetensorsWeights58.8 MB 4e19d4d8c47f
loras/voice-ru-m-bass-82/voice-ru-m-bass-82-e029.safetensorsWeights58.8 MB b7b2f04f3df4
models/SheetSage2-F32.ggufWeights2.7 GB 8a801a08cd27
models/SheetSage2-Q8_0.ggufWeights957.6 MB 4507d8c1d924
models/YuE2-3B-BF16.ggufWeights7.2 GB 668ca9ffa462
models/YuE2-3B-Q5_K_M.ggufWeights2.6 GB cd3efd250b73
models/YuE2-3B-Q6_K.ggufWeights2.9 GB 42068d5e5771
models/YuE2-3B-Q8_0.ggufWeights3.8 GB 41121ce97786
models/YuE2-Vae-F32.ggufWeights530.5 MB 93e49dfb1970
models/YuE2-Vae-blend-F32.ggufWeights530.5 MB 157b07f1487e
models/YuE2-Vae-legacy-F32.ggufWeights530.5 MB b632c2e607e7
sliders/acoustic-folk.ggufWeights15.9 MB 2d631c558eec
sliders/afrobeats.ggufWeights15.9 MB d23acd922ee0
sliders/country.ggufWeights15.9 MB d8f05ca53975
sliders/disco-funk.ggufWeights15.9 MB a82a124d46ee
sliders/female.ggufWeights15.9 MB 7e85e3bbe6de
sliders/hiphop.ggufWeights15.9 MB 15ad090a15e3
sliders/house.ggufWeights15.9 MB d7e5d93bd700
sliders/indie-rock.ggufWeights15.9 MB 836d82e1883e
sliders/kpop.ggufWeights15.9 MB cec833453a6f
sliders/lofi.ggufWeights15.9 MB 58586891d6e0
sliders/male.ggufWeights15.9 MB de7c55cc9d9b
sliders/metal.ggufWeights15.9 MB 9b2dda3c6677
sliders/pop-punk.ggufWeights15.9 MB ba412ac7ae65
sliders/pop.ggufWeights15.9 MB 6b8cf9f10ac1
sliders/reggaeton.ggufWeights15.9 MB 092d95395fd5
sliders/rnb.ggufWeights15.9 MB 44e32fb965df
universr/pytorch_model.binWeights229.1 MB eb99f98943cc
whisper/whisper-large-v3-ct2-float16/model.binWeights3.1 GB 69f74147e333
artwork/Qwen-Image-2.1/model_index.jsonConfiguration447 B —
artwork/Qwen-Image-2.1/processor/added_tokens.jsonConfiguration707 B —
artwork/Qwen-Image-2.1/processor/preprocessor_config.jsonConfiguration782 B —
artwork/Qwen-Image-2.1/processor/special_tokens_map.jsonConfiguration613 B —
artwork/Qwen-Image-2.1/processor/video_preprocessor_config.jsonConfiguration817 B —
artwork/Qwen-Image-2.1/scheduler/scheduler_config.jsonConfiguration485 B —
artwork/Qwen-Image-2.1/text_encoder/config.jsonConfiguration1.5 KB —
artwork/Qwen-Image-2.1/text_encoder/generation_config.jsonConfiguration213 B —
artwork/Qwen-Image-2.1/text_encoder/model.safetensors.index.jsonConfiguration67.8 KB —
artwork/Qwen-Image-2.1/transformer/config.jsonConfiguration370 B —
artwork/Qwen-Image-2.1/transformer/diffusion_pytorch_model.safetensors.index.jsonConfiguration30.3 KB —
artwork/Qwen-Image-2.1/vae/config.jsonConfiguration2.1 KB —
artwork/Qwen-Image-2512/model_index.jsonConfiguration443 B —
artwork/Qwen-Image-2512/scheduler/scheduler_config.jsonConfiguration485 B —
artwork/Qwen-Image-2512/text_encoder/config.jsonConfiguration3.1 KB —
artwork/Qwen-Image-2512/text_encoder/generation_config.jsonConfiguration244 B —
artwork/Qwen-Image-2512/text_encoder/model.safetensors.index.jsonConfiguration57.7 KB —
artwork/Qwen-Image-2512/tokenizer/added_tokens.jsonConfiguration605 B —
artwork/Qwen-Image-2512/tokenizer/special_tokens_map.jsonConfiguration613 B —
artwork/Qwen-Image-2512/transformer/config.jsonConfiguration339 B —
artwork/Qwen-Image-2512/vae/config.jsonConfiguration730 B —
artwork/Qwen3-4B-Instruct-2507/config.jsonConfiguration727 B —
artwork/Qwen3-4B-Instruct-2507/generation_config.jsonConfiguration238 B —
artwork/Qwen3-4B-Instruct-2507/model.safetensors.index.jsonConfiguration32.8 KB —
artwork/nsfw-filter/config.jsonConfiguration724 B —
artwork/nsfw-filter/preprocessor_config.jsonConfiguration325 B —
loras/YuE2-instrumental-cot-full-loras/scripts/ar_generate.pyConfiguration3.5 KB —
loras/YuE2-instrumental-cot-full-loras/scripts/ckpt_io.pyConfiguration1.6 KB —
separation/demucs/htdemucs_ft.yamlConfiguration149 B —
sliders/catalog.jsonConfiguration4.3 KB —
universr/config.yamlConfiguration533 B —
whisper/whisper-large-v3-ct2-float16/config.jsonConfiguration2.4 KB —
whisper/whisper-large-v3-ct2-float16/preprocessor_config.jsonConfiguration340 B —
whisper/whisper-large-v3-ct2-float16/vocabulary.jsonConfiguration1.1 MB —
LICENSEDocumentation20.3 KB —
LICENSE.mdDocumentation1.7 KB —
README.OLD.mdDocumentation11.7 KB —
README.mdDocumentation10.3 KB —
THIRD_PARTY_NOTICES.mdDocumentation4.9 KB —
artwork/Qwen-Image-2.1/LICENSEDocumentation7.8 KB —
artwork/Qwen-Image-2.1/NOTICEDocumentation347 B —
artwork/Qwen-Image-2.1/README.mdDocumentation5.7 KB —
artwork/Qwen-Image-2512/README.mdDocumentation19.3 KB —
artwork/Qwen3-4B-Instruct-2507/LICENSEDocumentation11.3 KB —
artwork/Qwen3-4B-Instruct-2507/README.mdDocumentation8.2 KB —
licenses/particle-sliders-LICENSE.txtDocumentation1.1 KB —
licenses/particle-sliders-LOADER_LICENSE.txtDocumentation1.1 KB —
listener/Qwen2.5-Omni-7B-GGUF/LICENSEDocumentation11.3 KB —
loras/YuE2-instrumental-cot-full-loras/README.mdDocumentation5.3 KB —
MANIFEST.tsvOther31.1 KB —
SHA256SUMSOther17.4 KB —
artwork/Qwen-Image-2.1/assets/qr.pngOther3.3 MB 9b1c6d8996a3
artwork/Qwen-Image-2.1/processor/chat_template.jinjaOther5.3 KB —
artwork/Qwen-Image-2512/tokenizer/chat_template.jinjaOther2.4 KB —
licenses/SnakeBeta-NVIDIA-MIT.txtOther1.1 KB —
licenses/stable-audio-tools-MIT.txtOther1.1 KB —
separation/demucs/04573f0d-f3cf25b2.thOther84.1 MB f3cf25b222c4
separation/demucs/92cfc3b6-ef3bcb9c.thOther84.1 MB ef3bcb9c8b40
separation/demucs/d12395a8-e57c48e6.thOther84.1 MB e57c48e6b0e3
separation/demucs/f7e0c4bc-ba3fe64a.thOther84.1 MB ba3fe64ae8ef
.gitattributesRepository4.9 KB —
loras/YuE2-instrumental-cot-full-loras/.gitattributesRepository1.5 KB —
artwork/Qwen-Image-2.1/processor/merges.txtTokenizer1.7 MB —
artwork/Qwen-Image-2.1/processor/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
artwork/Qwen-Image-2.1/processor/tokenizer_config.jsonTokenizer5.4 KB —
artwork/Qwen-Image-2.1/processor/vocab.jsonTokenizer2.8 MB —
artwork/Qwen-Image-2512/tokenizer/merges.txtTokenizer1.7 MB —
artwork/Qwen-Image-2512/tokenizer/tokenizer_config.jsonTokenizer4.7 KB —
artwork/Qwen-Image-2512/tokenizer/vocab.jsonTokenizer3.4 MB —
artwork/Qwen3-4B-Instruct-2507/merges.txtTokenizer1.7 MB —
artwork/Qwen3-4B-Instruct-2507/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
artwork/Qwen3-4B-Instruct-2507/tokenizer_config.jsonTokenizer9.4 KB —
artwork/Qwen3-4B-Instruct-2507/vocab.jsonTokenizer2.8 MB —
whisper/whisper-large-v3-ct2-float16/tokenizer.jsonTokenizer2.5 MB —

License and Download

License
other
Access
Open weights, no gate
Download size
239.6 GB
Download from Viktor Zhuromskyy

Released by Viktor Zhuromskyy through its official repository on Hugging Face.

Built From

  • Derived from Mothersuperior/YuE2-Vae-merge-0.666
  • Described by arXiv:2503.08638
  • Quantized from Mothersuperior/YuE2-Vae-merge-0.666

Memory Requirements

PrecisionWeights in memory
As published239.6 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About Ruach_Studio_Models_v2

What license is Ruach_Studio_Models_v2 released under?

other, as its publisher declares it. Read the license text before commercial use.

Similar Models

GGUF, Safetensors, and MLX quantized formats of Qwen/Qwen-Image-2.1 for local image generation using the original upstream base weights. Q4KM is recommended for the best balance of size and quality for GGUF. INT8 ConvRot and NVFP4 offer high performance on supported GPUs, while MLX formats are optimized for Apple Silicon. Companion model files packaged for ComfyUI: Use the model with ComfyUI and ComfyUI-GGUF. All required companion files (GGUF transformer, text encoder, and VAE) are hosted directly in this repository. Download the files and place them in their respective ComfyUI directories: 1. Install ComfyUI-GGUF: Use the maintained fork with native Qwen-Image 2.1 support by cloning…

Open weights other gguf
View model

GGUF quantizations of Qwen/Qwen-Image-2.1 for local image generation using the original upstream base weights. Q4KM is recommended for the best balance of size and quality. Companion model files packaged for ComfyUI: Use the model with ComfyUI and ComfyUI-GGUF. All required companion files (GGUF transformer, text encoder, and VAE) are hosted directly in this repository. Download the files and place them in their respective ComfyUI directories: 1. Install ComfyUI-GGUF: Use the maintained fork with native Qwen-Image 2.1 support by cloning leejet/ComfyUI-GGUF into your custom nodes: (Note: If you have the older city96/ComfyUI-GGUF installed and encounter an Unknown model architecture! error…

Open weights other gguf
View model

Model · Text to image

Qwen-Image-2.1-GGUF

Unsloth AI

This is a GGUF quantized version of Qwen-Image-2.1. unsloth/Qwen-Image-2.1-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. - Important layers are upcasted to higher precision, per tensor, from a measured sensitivity scan. - Run these with Unsloth Desktop, stable-diffusion.cpp and more. A GGUF is the denoiser only, so it needs the VAE and the Qwen3-VL text encoder alongside it. See below for image editing operating inside of Unsloth Desktop: Rendered with the Q4KM denoiser and the Q4KM text encoder, 1024x1024, 20 steps, cfg 6.0, euler. We are excited to open-source Qwen-Image-2.1, a unified text-to-image generation and image editing model in the Qwen family. With just 7B…

Open weights other
View model

Model · Text to image

Z-Image-Turbo-GGUF

Unsloth AI

Welcome to the official repository for the Z-Image（造相）project! Z-Image is a powerful and highly efficient image generation model with 6B parameters. Currently there are three variants: - Z-Image-Turbo – A distilled version of Z-Image that matches or exceeds leading competitors with only 8 NFEs (Number of Function Evaluations). It offers sub-second inference latency on enterprise-grade H800 GPUs and fits comfortably within 16G VRAM consumer devices. It excels in photorealistic image generation, bilingual text rendering (English & Chinese), and robust instruction adherence. - Z-Image-Base – The non-distilled foundation model. By releasing this checkpoint, we aim to unlock the full potential…

Open weights apache-2.0 ggml
View model

Model · Text to image

Juggernaut-XL-v9

RunDiffusion

The SDXL ecosystem is the single most mature corner of open image generation, and v9 is its most refined photorealism checkpoint. Choose Juggernaut XL v9 when you want: - Photorealism that holds up under scrutiny — skin texture, micro-contrast, and natural lighting that translates from concept to print. - Reasonable hardware — runs comfortably on 8 GB of VRAM, unlike newer DiT-based models that demand 16+ GB. - The full SDXL toolbox — drop-in compatibility with the thousands of SDXL ControlNets, IP-Adapter variants, AnimateDiff, regional prompting tools, and LoRAs already in your workflow. - Battle-tested reliability — 26+ months in production, used in agencies, studios, and shipping…

Open weights creativeml-openrail-m diffusers
View model

Model · Text to image

Qwen-Image-Lightning

Lightx2v

Please refer to Qwen-Image-Lightning github to learn how to use the models. make sure to install diffusers from main (pip install git+https://github.com/huggingface/diffusers.git)

Open weights apache-2.0 diffusers
View model