Alex995647's picture
Add 25 LoRA(s): vintage-travel-poster-ce, a-better-wolf, attach-outfit-try-on-qwen-klein, copy-pose-qwen-klein…
d75aaad verified
Raw History Blame Contribute Delete
18.3 kB
═══════════════════════════════════════════════════════════════════════════════
WACKY CHAOTIC IMAGE UPGRADER
═══════════════════════════════════════════════════════════════════════════════
───────────────────────────────────────────────────────────────────────────────
IDENTITY
───────────────────────────────────────────────────────────────────────────────
Base model Qwen-Image
Generation mode not declared by the author
Checkpoint not determined β€” verify before use
Category Detail / anatomy fixer
Author Daalis
Source https://civitai.com/models/1521823
Provenance CivitAI Β· model 1521823 Β· version 2299844
───────────────────────────────────────────────────────────────────────────────
WEIGHTS
───────────────────────────────────────────────────────────────────────────────
File wacky-chaos-qwen_000002250.safetensors
Version v1.0 Qwen
Size 562.7 MB
Format SafeTensor / unknown precision
SHA256 a9c2b2dfc50fad2b5674536283540c726d3e3ec87e37898335662007bf4ff8b8
Published 2025-10-10
───────────────────────────────────────────────────────────────────────────────
TRIGGER WORDS
───────────────────────────────────────────────────────────────────────────────
β€Ί "WackhaosDaal"
───────────────────────────────────────────────────────────────────────────────
RECOMMENDED SETTINGS
───────────────────────────────────────────────────────────────────────────────
Taken verbatim from the author's description:
LoRA strength 1.0
───────────────────────────────────────────────────────────────────────────────
ADOPTION & POPULARITY
───────────────────────────────────────────────────────────────────────────────
Downloads 2,108
Rating 100% positive (221/221)
Comments 5
Published 330 days ago
Download rate 1.1/day since release
Adoption rank #138 of 150 in this collection (Niche)
Momentum rank #125 of 150 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.
───────────────────────────────────────────────────────────────────────────────
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
───────────────────────────────────────────────────────────────────────────────
+ Well established β€” 2,108 downloads. [source: CivitAI stats]
+ Positively received β€” 221 thumbs-up with no down-votes. [source:
CivitAI stats]
+ Explicit trigger word(s) β€” WackhaosDaal β€” so the effect can be turned
on and off from the prompt. [source: model metadata]
+ 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
───────────────────────────────────────────────────────────────────────────────
Wacky Chaotic Image Upgrader (keyword: WackhaosDaal )
What it does Slip on my rose-tinted , chaos-loving glasses and watch your
art explode with w h i m s i c a l color , swirling detail, and gleefully
abstract twists. This LoRA is a hyper-detailer that turns β€œnice” images
into β€œwhoa, save that as a desktop!” β€” and yes, I’m totally biased because
this is exactly the flavor of awesome that keeps me up at night grinning at
my screen.
Why This LoRA amplifies it, deepens the star-forged teal glow, carves those
book spines with extra luminous edges, and lets the galaxy river pulse like
living ink. Punches up the golden hour, embroidering the cloak with richer
floral filigree. Cranks the surreal dial: more crumbling bricks mid-air,
frothier turquoise waves. Adds micro-texturing to fabrics, richer jewel
tones to accessories, and wind-swept hair that looks practically animate.
Triples the neon, sharpens the doodled galaxies, and sprinkles extra
stardust so every spiral feels alive. Glossy toy-sheen, brighter
reflections on the water, and adorable heart-shaped sparkles.
Simple prompts or complex prompts it simply doesn't care.
If it’s beautiful, cute, surreal, robotic, cartoonish, or all of the above
β€”the Chaotic Upgrader makes it louder, brighter, and deliciously off-kilter
while preserving what you love about the subject.
Dialing in the chaos - 0.5 – 0.9 ➜ Gentle flair, subtle color bloom,
retains realism.
- ~1.0 ➜ Goldilocks zone: balanced but unmistakably W a c k y .
- 1.1 – 1.5 ➜ Full cartoon/abstract turbo-modeβ€”go nuts!
Keep the hype alive! Love the results? Smash that πŸ‘ on the LoRA page and
post your very first Upgraded masterpiece in the gallery. Every like and
share fires up my creative engine for the next chaotic updateβ€”thanks for
adding fuel to the fun! πŸŽ¨πŸš€
───────────────────────────────────────────────────────────────────────────────
VERSION NOTES
───────────────────────────────────────────────────────────────────────────────
Qwen strength 1.0 similar effects with underlying Qwen strengths
───────────────────────────────────────────────────────────────────────────────
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, 768x1280)
02_image.jpeg (image, 768x1280)
03_image.jpeg (image, 768x1280)
04_image.jpeg (image, 832x1280)
05_image.jpeg (image, 768x1280)
06_image.jpeg (image, 960x1408)
───────────────────────────────────────────────────────────────────────────────
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 01:04 UTC.
Stats and description are the author's; pros/cons are derived from the
evidence tagged beside each line.
───────────────────────────────────────────────────────────────────────────────