Instructions to use Alex995647/loras-qwen-image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Alex995647/loras-qwen-image with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image-2512", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Alex995647/loras-qwen-image") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
Add 18 LoRA(s): qwen-edit-2509-openpose, 2dhd-pixel-art-octopath-style, cinematic-photography-qwen2512, american-cartoon-styleβ¦
582776f verified Download glasses-asian-women-with-glasses-ultra-realistic-multi/info.txt from Alex995647/loras-qwen-image: direct link, hf CLI and curl.
- Browser
- Download file 18.2 kB
-
https://huggingface.co/Alex995647/loras-qwen-image/resolve/main/glasses-asian-women-with-glasses-ultra-realistic-multi/info.txt
- Command line
-
hf download hf://Alex995647/loras-qwen-image/glasses-asian-women-with-glasses-ultra-realistic-multi/info.txt
-
curl -L -o info.txt https://huggingface.co/Alex995647/loras-qwen-image/resolve/main/glasses-asian-women-with-glasses-ultra-realistic-multi/info.txt
18.2 kB
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| GLASSES - [ASIAN WOMEN WITH GLASSES , ULTRA REALISTIC, MULTI PURPOSE] | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| IDENTITY | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| Base model Qwen-Image | |
| Generation mode not declared by the author | |
| Checkpoint not determined β verify before use | |
| Category Photorealism | |
| Author Dead_Sec | |
| Source https://civitai.com/models/1749278 | |
| Provenance CivitAI Β· model 1749278 Β· version 2483853 | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| WEIGHTS | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| File spec_gurl.safetensors | |
| Version Qwen - Beta | |
| Size 281.5 MB | |
| Format SafeTensor / unknown precision | |
| SHA256 e5df8f7f521faa5b8941b16a401e50ac70c80154104484b3a605e52f700d831d | |
| Published 2025-12-08 | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| TRIGGER WORDS | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| βΊ "sp3c_6ur7" | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| RECOMMENDED SETTINGS | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| Taken verbatim from the author's description: | |
| LoRA strength 0.6β1.0 | |
| Sampler steps 110 | |
| Resolution 512x512 | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| ADOPTION & POPULARITY | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| Downloads 982 | |
| Rating 100% positive (42/42) | |
| Comments 0 | |
| Published 274 days ago | |
| Download rate 1.3/day since release | |
| Adoption rank #169 of 200 in this collection (Niche) | |
| Momentum rank #178 of 200 by download rate (Long tail) | |
| Adoption tier is the percentile of total downloads within this collection; | |
| momentum is the percentile of downloads-per-day since release. Momentum is | |
| ranked rather than measured against a fixed rate, because this base model | |
| is itself new and every LoRA looks fast on an absolute scale. Both numbers | |
| are CivitAI's, read on the scrape date at the foot of this file. | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| CHAINING / STACKING | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| Stacks with others not stated | |
| The author gave no chaining guidance. The rules below are the | |
| general Qwen-Image ones, not anything specific to this LoRA. | |
| General Qwen-Image rules that apply here (see REFERENCE.txt): | |
| β’ Stack by wiring LoraLoaderModelOnly nodes in series on the MODEL line. | |
| This is the officially shipped pattern: | |
| template_qwen_Image_2512_360_lora chains Qwen- | |
| Image-2512-Lightning-4steps-V1.0-fp32 at 1.0 into | |
| qwen-360-diffusion-2512-int8-bf16-v2 at 1.0. | |
| β’ One accelerator LoRA maximum. Every official template loads exactly one | |
| Lightning/Turbo LoRA, and ComfyUI's Qwen-Image docs record that the | |
| fully-distilled checkpoint and the lightx2v 8-step LoRA are not usable | |
| together. | |
| β’ Match the accelerator to the checkpoint family: Qwen- | |
| Image-2512-Lightning on 2512, Qwen-Image-Lightning on the August base, | |
| the Edit-2509 subfolder LoRAs on Edit-2509, Qwen-Image- | |
| Edit-2511-Lightning on Edit-2511. lightx2v distilled and shipped these | |
| separately per family. | |
| β’ When any accelerator LoRA is in the chain, move the sampler to that | |
| LoRA's step count and cfg 1.0. Leaving cfg at 4.0 with a distilled LoRA | |
| is the most common bad-output cause. | |
| β’ Order used by the official templates: accelerator LoRA adjacent to the | |
| base loader, concept/style LoRA after it, then ModelSamplingAuraFlow, | |
| then the sampler (the 360-panorama template's exact order). | |
| β’ Keep the summed strength of concept/style LoRAs roughly in the 0.9-1.2 | |
| band (CivitAI article 18798). The accelerator LoRA sits outside that | |
| budget at its own 1.0. | |
| β’ Control LoRAs (qwen_image_union_diffsynth_lora.safetensors) chain like | |
| ordinary LoRAs and combine with an accelerator: the official 'Qwen- | |
| Image Union Control' template stacks the control LoRA with Qwen-Image- | |
| Lightning-4steps-V1.0, both at 1.0, sampling at 4 steps / cfg 1.0 / | |
| shift 3.1. | |
| β’ Be conservative stacking older Edit LoRAs on Edit-2511: the Qwen README | |
| says community LoRA effects were merged into the 2511 base, so those | |
| LoRAs can double-apply. | |
| β’ The author never states which weight family this targets. Mismatch is | |
| silent degradation, essentially never a hard error. Every Qwen-Image | |
| weight family resolves to the same ComfyUI model class | |
| (comfy.model_base.QwenImage, unet_config image_model "qwen_image", | |
| latent_format Wan21, built-in sampling shift 1.15 - | |
| comfy/supported_models.py | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| PROS | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| + Explicit trigger word(s) β sp3c_6ur7 β so the effect can be turned on | |
| and off from the prompt. [source: model metadata] | |
| + Compact at 281 MB β cheap to stack with other LoRAs. [source: file | |
| size] | |
| + Author published concrete recommended settings. [source: description] | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| CONS & CAVEATS | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| - Author never states which generation mode it was trained for; test | |
| against your own workflow before relying on it. [source: description] | |
| - Modest adoption (982 downloads) β less community feedback to rely on. | |
| [source: source stats] | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| COMPATIBILITY WARNING | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| Mismatch is silent degradation, essentially never a hard error. Every Qwen- | |
| Image weight family resolves to the same ComfyUI model class | |
| (comfy.model_base.QwenImage, unet_config image_model "qwen_image", | |
| latent_format Wan21, built-in sampling shift 1.15 - | |
| comfy/supported_models.py), and the bf16/fp8 file sizes are identical | |
| across Qwen-Image, Qwen-Image-2512, Qwen-Image-Edit, Edit-2509 and | |
| Edit-2511. So a LoRA trained on any of them will key-match and load against | |
| any other. Where keys genuinely do not match, ComfyUI only logs `lora key | |
| not loaded: <key>` (comfy/lora.py:93) and continues; a shape mismatch logs | |
| `WARNING SHAPE MISMATCH <key> WEIGHT NOT MERGED` (comfy/lora.py:498) and | |
| skips that tensor. Both are console warnings; the render still completes. | |
| Verified consequence: lightx2v re-distilled and re-released Lightning | |
| weights separately for Qwen-Image, Qwen-Image-Edit, Edit-2509, Edit-2511 | |
| and Qwen-Image-2512, so accelerators are family- specific in practice. The | |
| one documented case worse than mild degradation is precision-level, not | |
| family-level: bf16-trained LoRAs on the naive | |
| qwen_image_fp8_e4m3fn.safetensors base produce grid artifacts, stated | |
| outright in the ModelTC/Qwen-Image-Lightning README. Whether an Edit LoRA | |
| on the T2I base merely no-ops (no ref_latents conditioning is supplied) or | |
| a T2I LoRA on an Edit checkpoint transfers as a style push is inference | |
| from the architecture, not a sourced statement - see unverified. | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| AUTHOR'S DESCRIPTION | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| Title: spec_gurl-v1 β Realistic Woman with Glasses [Close-up Character | |
| LoRA] | |
| Description: | |
| spec_gurl-v1 is a realistic LoRA character trained on a carefully curated | |
| dataset of women wearing glasses. This LoRA is ideal for generating high- | |
| quality portraits and close-up shots of a female character who consistently | |
| features glasses as a defining trait. | |
| Perfect for cinematic renders, social-style photos, and expressive | |
| character studies, this LoRA preserves facial structure, skin detail, and | |
| lens reflections across multiple angles. | |
| π Details: - Trigger word: spec_gurl | |
| - Model Base: SD1.5 ( runwayml/stable-diffusion-v1-5 ) | |
| - Clip Skip: 2 | |
| - Resolution: Trained with mixed resolutions ( 512x512 , 576x512 , 640x512 | |
| ) | |
| - Supports bucketed resolutions up to 512x768 and beyond | |
| - Training: | |
| - 102 images | |
| - 10 batch size | |
| - 10 epochs | |
| - 110 steps | |
| - Trained using Kohya LoRA ( networks.lora ) | |
| - File Size: 72MB | |
| - Hash: 89ed443e37f0 | |
| π§ͺ Recommended Usage: - Prompt: spec_gurl <lora:spec_gurl-v1:0.95>, close- | |
| up, glasses, ultra-detailed face, natural lighting, bokeh background Pair | |
| with <lora:add_detail:1.8> for enhanced realism. | |
| - Recommended LoRA weight: 0.6 β 1.0 | |
| - Best With: | |
| - add_detail , epi_noiseoffset , clearVAE , easynegative | |
| - Realistic base models like CyberRealistic , RealisticVision , or your | |
| custom blends | |
| - Notes: | |
| - Works best in portrait or half-body framing | |
| - Facial features remain consistent even at high-res | |
| - Character identity focuses on a realistic woman who always wears glasses | |
| π·οΈ Suggested Tags: realistic, portrait, female, glasses, woman, photo, | |
| photorealistic, character, close-up, lora, sd1.5, cinematic, detail, kohya, | |
| clip-skip-2, curated-dataset, 512x768, multi-angle, bucket-train | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| VERSION NOTES | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| Qwen Ver , use trigger word : sp3c_6ur7 | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| EXAMPLE MEDIA | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| 2 preview(s) in ./example_images/ β community results for | |
| this LoRA. Videos keep a matching _poster.jpg still frame. | |
| No prompts are recorded below: CivitAI's public API flags these posts as | |
| having generation metadata but does not return it, so the prompts cannot be | |
| scraped. Open the model page to read them. | |
| 01_image.jpeg (image, 1104x1472) | |
| 02_image.jpeg (image, 1104x1472) | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| HOW TO USE (COMFYUI) | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| 1. Update ComfyUI first - Qwen-Image support is native, but each new family | |
| member (Edit-2509, Edit-2511, 2512) needed a fresh release, so an old build | |
| will not detect the checkpoint. | |
| 2. Put the base checkpoint in `ComfyUI/models/diffusion_models/` - e.g. | |
| `qwen_image_2512_fp8_e4m3fn.safetensors` (20.43 GB, the file the official | |
| 2512 template names) or `qwen_image_2512_bf16.safetensors` (40.86 GB), from | |
| huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/split_files/diffusion_models. | |
| Edit checkpoints come from Comfy-Org/Qwen-Image-Edit_ComfyUI. Load with | |
| `Load Diffusion Model` (UNETLoader), not a checkpoint loader - these are | |
| unet-only files. | |
| 3. Put `qwen_2.5_vl_7b_fp8_scaled.safetensors` (9.38 GB) in | |
| `ComfyUI/models/text_encoders/` and load with `Load CLIP` (CLIPLoader), | |
| type `qwen_image`. Every official template uses exactly this pair. | |
| 4. Put `qwen_image_vae.safetensors` in `ComfyUI/models/vae/` and load with | |
| `Load VAE`. | |
| 5. Put LoRA `.safetensors` in `ComfyUI/models/loras/`. Subfolders show up | |
| as `subfolder/name.safetensors` in the dropdown - useful for separating t2i | |
| / edit / accelerator LoRAs. | |
| 6. Load with `LoraLoaderModelOnly`, patching only the MODEL line between | |
| the UNETLoader and ModelSamplingAuraFlow. Every official Comfy-Org Qwen | |
| template uses LoraLoaderModelOnly; the two-output `LoraLoader` also works | |
| but its CLIP branch is a no-op for DiT-only LoRAs. | |
| 7. Insert `ModelSamplingAuraFlow` after the LoRA chain. Use 3.1 for T2I and | |
| Edit-2511, 3.0 for the 2-step Turbo and Edit-2509 templates. Without this | |
| node ComfyUI uses the model's built-in shift of 1.15 and results differ | |
| from every published example. | |
| 8. Set KSampler to euler / simple / denoise 1.0, then steps+cfg per the | |
| accelerator (50/4.0 plain, 8/1.0 or 4/1.0 with Lightning, 2/1.0 with the | |
| 2-step Turbo). Latent from `EmptySD3LatentImage` at an official resolution. | |
| 9. Low-VRAM alternative: the `ComfyUI-GGUF` custom node with `Unet Loader | |
| (GGUF)` and a Qwen-Image/2512 GGUF (unsloth/Qwen-Image-2512-GGUF). LoRA | |
| loading still goes through LoraLoaderModelOnly, placed after the GGUF | |
| loader. | |
| 10. For Edit workflows, swap CLIPTextEncode for `TextEncodeQwenImageEdit` | |
| (single image) or `TextEncodeQwenImageEditPlus` (2509/2511) and add a | |
| `CFGNorm` node as the Edit-2511 template does; the LoRA chain sits in the | |
| same place. | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| Scraped by lorakit on 2026-09-08 13:32 UTC. | |
| Stats and description are the author's; pros/cons are derived from the | |
| evidence tagged beside each line. | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |