Alex995647's picture
Add 25 LoRA(s): qwen-edit-figure-maker-by-aldniki, pixelartredmond-pixel-art-loras, movie-poster-ce, clothes-try-on-clothing-transfer-qwen-edit…
d11d14f verified
Raw History Blame Contribute Delete
19.1 kB
═══════════════════════════════════════════════════════════════════════════════
GHIBLI STYLE (KIKI'S DELIVERY SERVICE)
═══════════════════════════════════════════════════════════════════════════════
───────────────────────────────────────────────────────────────────────────────
IDENTITY
───────────────────────────────────────────────────────────────────────────────
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
───────────────────────────────────────────────────────────────────────────────
WEIGHTS
───────────────────────────────────────────────────────────────────────────────
File ghibli_style_qwen_v3.safetensors
Version Qwen v3
Size 281.5 MB
Format SafeTensor / unknown precision
SHA256 20d2038be996c9e777cbbe3247c524e45ddc7cacdadcaee82e2e81b7921335c1
Published 2025-12-27
───────────────────────────────────────────────────────────────────────────────
TRIGGER WORDS
───────────────────────────────────────────────────────────────────────────────
β€Ί "ghibli style"
───────────────────────────────────────────────────────────────────────────────
RECOMMENDED SETTINGS
───────────────────────────────────────────────────────────────────────────────
Taken verbatim from the author's description:
LoRA strength 1.3
Sampler steps 8
Resolution 768x1152
CFG / guidance 1
Sampler Euler
───────────────────────────────────────────────────────────────────────────────
ADOPTION & POPULARITY
───────────────────────────────────────────────────────────────────────────────
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.
───────────────────────────────────────────────────────────────────────────────
CHAINING / STACKING
───────────────────────────────────────────────────────────────────────────────
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
───────────────────────────────────────────────────────────────────────────────
PROS
───────────────────────────────────────────────────────────────────────────────
+ 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]
───────────────────────────────────────────────────────────────────────────────
CONS & CAVEATS
───────────────────────────────────────────────────────────────────────────────
- Author never states which generation mode it was trained for; test
against your own workflow before relying on it. [source: description]
───────────────────────────────────────────────────────────────────────────────
COMPATIBILITY WARNING
───────────────────────────────────────────────────────────────────────────────
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.
───────────────────────────────────────────────────────────────────────────────
AUTHOR'S DESCRIPTION
───────────────────────────────────────────────────────────────────────────────
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...)
───────────────────────────────────────────────────────────────────────────────
VERSION NOTES
───────────────────────────────────────────────────────────────────────────────
- Trigger word is now "ghibli style"
- More flexible
───────────────────────────────────────────────────────────────────────────────
EXAMPLE MEDIA
───────────────────────────────────────────────────────────────────────────────
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)
───────────────────────────────────────────────────────────────────────────────
HOW TO USE (COMFYUI)
───────────────────────────────────────────────────────────────────────────────
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.
───────────────────────────────────────────────────────────────────────────────
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.
───────────────────────────────────────────────────────────────────────────────