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
18.6 kB
═══════════════════════════════════════════════════════════════════════════════
RAW COLOR
═══════════════════════════════════════════════════════════════════════════════
───────────────────────────────────────────────────────────────────────────────
IDENTITY
───────────────────────────────────────────────────────────────────────────────
Base model Qwen-Image
Generation mode not declared by the author
Checkpoint not determined β€” verify before use
Category Visual style
Author Daalis
Source https://civitai.com/models/2054832
Provenance CivitAI Β· model 2054832 Β· version 2346806
───────────────────────────────────────────────────────────────────────────────
WEIGHTS
───────────────────────────────────────────────────────────────────────────────
File raw-color-qwen-v2.safetensors
Version v1.0 Qwen
Size 562.7 MB
Format SafeTensor / unknown precision
SHA256 091468973ca78172a0bdb4ebc120bb5fb1e33e15a86bb9fa98a0485cd9104288
Published 2025-10-25
───────────────────────────────────────────────────────────────────────────────
TRIGGER WORDS
───────────────────────────────────────────────────────────────────────────────
β€Ί "RawColorDaal"
───────────────────────────────────────────────────────────────────────────────
RECOMMENDED SETTINGS
───────────────────────────────────────────────────────────────────────────────
Taken verbatim from the author's description:
LoRA strength 1.0
───────────────────────────────────────────────────────────────────────────────
ADOPTION & POPULARITY
───────────────────────────────────────────────────────────────────────────────
Downloads 2,069
Rating 100% positive (177/177)
Comments 5
Published 314 days ago
Download rate 1.6/day since release
Adoption rank #140 of 150 in this collection (Niche)
Momentum rank #101 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€” 2,069 downloads. [source: CivitAI stats]
+ Positively received β€” 177 thumbs-up with no down-votes. [source:
CivitAI stats]
+ Explicit trigger word(s) β€” RawColorDaal 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
───────────────────────────────────────────────────────────────────────────────
Raw Color β€” A LoRA for Expressive, Unfinished Beauty Unlock a world of
vibrant, textured imperfection. β€œRaw Color” is a LoRA designed to bring
painterly looseness and emotional intensity into your generations. From
sketchy portraits to dreamlike scenes, it evokes the feeling of art still
in motion. Where brushstrokes are visible, edges are intentional, and the
story is never quite finished.
About the Style Raw Color thrives in the space between polish and process.
Think digital canvases where the underpainting shows through, or concept
art just before final render. It leans into:
- Tactile brushwork and smudged edges
- Expressive faces and figures often caught mid-thought
- Bold, unapologetic color palettes
- A mix of real-world and surreal subject matter
- A look that feels equal parts fashion sketch , storybook , cyberpunk zine
, and indie animation frame
It pairs especially well with prompts involving emotion, movement, and
visual storytelling.
Recommended Weights To get the best out of Raw Color, here’s what I’ve
found works:
- Flux : A weight of 1.0 works well, strong lines, confident texture.
- Illustrious : Results vary a bit more depending on the base checkpoint.
Try between 0.7 and 1.0 and adjust based on how much texture or rawness you
want in the final image.
- I am working on a Qwen version - TBD
Don’t be afraid to push into moody lighting or add descriptive terms like
β€œunfinished,” β€œbrushwork,” or β€œconcept art” to reinforce the look.
Share Your Generations! If you create something beautiful (or weird, or
wild, or poetic) with Raw Color, I’d love to see it! Upload your images to
Civitai and tag this LoRA, it helps others find it and supports further
development.
Please Rate & Review If this LoRA resonated with your creative style, drop
a rating or comment. Your feedback helps shape future updates and lets
other artists discover the LoRA faster.
───────────────────────────────────────────────────────────────────────────────
VERSION NOTES
───────────────────────────────────────────────────────────────────────────────
Qwen version gave me more trouble than I was expecting. Generally happy
with the final results but it took several tweaks, tunes, and even a
different set of images. Anyway, Strength of 1.0 works well if you see Qwen
smoothing things out go a little higher.
───────────────────────────────────────────────────────────────────────────────
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, 768x1280)
05_image.jpeg (image, 768x1280)
06_image.jpeg (image, 768x1280)
───────────────────────────────────────────────────────────────────────────────
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 01:05 UTC.
Stats and description are the author's; pros/cons are derived from the
evidence tagged beside each line.
───────────────────────────────────────────────────────────────────────────────