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 25 LoRA(s): qwen-edit-figure-maker-by-aldniki, pixelartredmond-pixel-art-loras, movie-poster-ce, clothes-try-on-clothing-transfer-qwen-editβ¦
d11d14f verified Download ghibli-style-kiki-s-delivery-service/info.txt from Alex995647/loras-qwen-image: direct link, hf CLI and curl.
- Browser
- Download file 19.1 kB
-
https://huggingface.co/Alex995647/loras-qwen-image/resolve/main/ghibli-style-kiki-s-delivery-service/info.txt
- Command line
-
hf download hf://Alex995647/loras-qwen-image/ghibli-style-kiki-s-delivery-service/info.txt
-
curl -L -o info.txt https://huggingface.co/Alex995647/loras-qwen-image/resolve/main/ghibli-style-kiki-s-delivery-service/info.txt
19.1 kB
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| GHIBLI STYLE (KIKI'S DELIVERY SERVICE) | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| IDENTITY | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| Base model Qwen-Image | |
| Generation mode not declared by the author | |
| Checkpoint not determined β verify before use | |
| Category Visual style | |
| Author Yofaraway | |
| Source https://civitai.com/models/523485 | |
| Provenance CivitAI Β· model 523485 Β· version 2540186 | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| WEIGHTS | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| File ghibli_style_qwen_v3.safetensors | |
| Version Qwen v3 | |
| Size 281.5 MB | |
| Format SafeTensor / unknown precision | |
| SHA256 20d2038be996c9e777cbbe3247c524e45ddc7cacdadcaee82e2e81b7921335c1 | |
| Published 2025-12-27 | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| TRIGGER WORDS | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| βΊ "ghibli style" | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| RECOMMENDED SETTINGS | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| Taken verbatim from the author's description: | |
| LoRA strength 1.3 | |
| Sampler steps 8 | |
| Resolution 768x1152 | |
| CFG / guidance 1 | |
| Sampler Euler | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| ADOPTION & POPULARITY | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| Downloads 8,925 | |
| Rating 100% positive (604/605) | |
| Comments 0 | |
| Published 252 days ago | |
| Download rate 5.1/day since release | |
| Adoption rank #38 of 150 in this collection (High) | |
| Momentum rank #52 of 150 by download rate (Steady) | |
| 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 | |
| + Widely adopted β 8,925 downloads. [source: CivitAI stats] | |
| + Positively received β 604 thumbs-up, 1 down. [source: CivitAI stats] | |
| + Explicit trigger word(s) β ghibli style 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] | |
| 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 | |
| KREA 2 Showcase images : | |
| - Turbo model | |
| - Euler / simple / 8 steps / CFG 1 | |
| - 768x1152 | |
| - Lora strength of 1.3 | |
| IDEOGRAM 4 Used json captioning with art_style : "Studio Ghibli style" and | |
| medium : "anime_screencap" | |
| v2 : Try other settings and the style seems a bit better with this one | |
| v1 : First training on Ideogram4 | |
| ANIMA First Lora trained on Anima, and it seems really good for a first | |
| try. | |
| Showcase images : | |
| - er_sde / simple / 30 steps / CFG 5 | |
| - 768x1152 | |
| - Lora strength of 1 | |
| KLEIN 9B v1 : | |
| Showcase images were generated with the base model, but I've posted same | |
| prompt images with the distilled one which are way better imo. None of the | |
| images were upscaled. | |
| ZIB v1 : | |
| First time training a Z-image Base lora, so still experimenting. Showcase | |
| images : | |
| - Euler / normal / 20 steps / CFG 5 | |
| - Hires steps : 20 / NMKD_SIAX @0.2-0.5 / x1.5-x2 | |
| - 768x1152 | |
| - Lora strength of 1 | |
| QWEN v3 : | |
| After training way more qwen loras, I've tried to apply everything I've | |
| learned with this one. Trigger word is now simply 'ghibli style' | |
| It should be more flexible and closer to the style of the movie. But to do | |
| characters of the movie, v2 is better. v2 : I've experimented way more with | |
| qwen training and this version is way better than v1. The lora is a bit big | |
| (600mo) because it's like 18k steps. And I've added a trigger token for the | |
| style : 'KikiLaPetiteSorciere style' To generate all images, I've used | |
| Qwen-Image (BF16) + Lightning Lora (4 steps) + my lora with weight of 1. | |
| DDIM with Beta, 4 steps, CFG 1. | |
| For some of them, I've upscaled with my flux lora version of this one, and | |
| this workflow. | |
| v1 : | |
| First qwen-image lora i've trained. I'm still testing and learning | |
| FLUX First attempt at a Flux Lora (trained on Civitai). | |
| The dataset consists of 28 screencaps (1920 Γ 1024) from the Ghibli movie | |
| Kiki's Delivery Service by Hayao Miyazaki. | |
| I used Florence2 to caption the images, then manually corrected the | |
| captions to fix any accuracy errors and to add the trigger phrase: | |
| 'a KikiLaPetiteSorciere style image of' | |
| SDXL Trigger words : KikiLaPetiteSorciere style | |
| For the character Kiki : kiki (majo no takkyuubin), red bow | |
| Trained on 1000 images screencap from the movie Kiki's Delivery Service by | |
| Hayao Miyazaki | |
| All images displayed were made with Dreamshaper XL Lightning : | |
| Lora's strength of 1 | |
| 1216x832 | |
| CFG 2 | |
| 6 steps | |
| DPM++ SDE Karras | |
| Clip skip 2 | |
| Only the jedi one was inpainted (she had 3 legs...) | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| VERSION NOTES | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| - Trigger word is now "ghibli style" | |
| - More flexible | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| EXAMPLE MEDIA | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| 6 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, 1056x1584) | |
| 02_image.jpeg (image, 1056x1584) | |
| 03_image.jpeg (image, 1056x1584) | |
| 04_image.jpeg (image, 1056x1584) | |
| 05_image.jpeg (image, 1056x1584) | |
| 06_image.jpeg (image, 1056x1584) | |
| 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 2026-09-05 00:57 UTC. | |
| Stats and description are the author's; pros/cons are derived from the | |
| evidence tagged beside each line. | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |