tiny-things/info.txt

═══════════════════════════════════════════════════════════════════════════════
  TINY THINGS
═══════════════════════════════════════════════════════════════════════════════

───────────────────────────────────────────────────────────────────────────────
  IDENTITY
───────────────────────────────────────────────────────────────────────────────
  Base model        Qwen-Image
  Generation mode   not declared by the author
  Checkpoint        not determined — verify before use
  Category          Detail / anatomy fixer
  Author            Daalis
  Source            https://civitai.com/models/2313869
  Provenance        CivitAI · model 2313869 · version 2611816

───────────────────────────────────────────────────────────────────────────────
  WEIGHTS
───────────────────────────────────────────────────────────────────────────────
  File              Tiny Things Qwen.safetensors
  Version           v1.0 Qwen
  Size              562.7 MB
  Format            SafeTensor / unknown precision
  SHA256            ca2b83ad558904a7e5f7c834769c221d0d8d2c3fb332866111356269a808de41
  Published         2026-01-19

───────────────────────────────────────────────────────────────────────────────
  TRIGGER WORDS
───────────────────────────────────────────────────────────────────────────────
  › "TinyDaal"

───────────────────────────────────────────────────────────────────────────────
  RECOMMENDED SETTINGS
───────────────────────────────────────────────────────────────────────────────
  Taken verbatim from the author's description:

  LoRA strength       1.0

───────────────────────────────────────────────────────────────────────────────
  ADOPTION & POPULARITY
───────────────────────────────────────────────────────────────────────────────
  Downloads               3,740
  Rating                  100% positive (316/316)
  Comments                0
  Published               228 days ago
  Download rate           1.9/day since release

  Adoption rank           #90 of 150 in this collection  (Modest)
  Momentum rank           #90 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):

  • 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.
  • 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.
  • 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.
  • 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.
  • 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).
  • 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.
  • 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.
  • 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.
  • 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 — 3,740 downloads. [source: CivitAI stats]
  + Positively received — 316 thumbs-up with no down-votes. [source:
    CivitAI stats]
  + Explicit trigger word(s) — TinyDaal — so the effect can be turned on
    and off from the prompt. [source: model metadata]
  + Author published concrete recommended settings. [source: description]

───────────────────────────────────────────────────────────────────────────────
  CONS & CAVEATS
───────────────────────────────────────────────────────────────────────────────
  - Needs a reduced strength; the default 1.0 is likely too strong.
    [source: description]
  - 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
───────────────────────────────────────────────────────────────────────────────
  Tiny Things Tiny Things is a stylistic/concept LoRA that transforms images
  into a world of extreme scale inversion, fragile miniatures, and tactile
  macro surrealism. When activated with the keyword TinyDaal , it encourages
  subjects to appear impossibly small and delicately constructed, often
  (maybe a little too often) doll-like, porcelain-smooth, stitched, wired, or
  worn (I do like weird stuff so...); set against environments that feel
  vast, quiet, and softly indifferent. The style emphasizes material realism
  over anatomy: cracks, fibers, rust, glaze, dust, and subtle imperfections
  are as important as the subject itself. The overall mood leans toward
  poetic melancholy, restrained whimsy, and intimate stillness rather than
  spectacle or action.
  You may have seen from the images I generate myself that I am a fan of tiny
  and small things. This is a labor of that fascination and adoration and
  involved a lot of curation, testing, and more than the usual data set
  tuning. I am quite happy with zImage and Flux is ok (it tends to push a bit
  more photorealistic than I would like) and I am thrilled with how capable
  Illustrious came out.
  The LoRA performs best at a strength of 1.0 , with a useful range between
  0.5 and 1.5 . Lower strengths allow more deviation toward standard image
  appearance, while higher strengths push deeper into the Tiny Things
  aesthetic. It has shown strong results across animals, people, objects,
  places, and full scenes , though very complex or heavily conflicting prompt
  instructions may reduce stylistic adherence. Simpler compositions and clear
  subjects tend to showcase the style most effectively.
  Activation & Usage - Trigger word: TinyDaal

  - Recommended strength: 1.0

  - Usable range: 0.5 – 1.5

  - Works well with macro, miniature, surreal, fantasy, and quiet character-
  focused prompts

  Helpful prompt hints for best results:
  macro photography, extreme scale contrast, miniature subject, tiny figure,
  fragile, delicate, doll-like, porcelain, ceramic, stitched fabric, wire,
  paper fibers, dust particles, cracks, imperfections, worn textures,
  handcrafted, tactile materials, shallow depth of field, soft directional
  light, overcast lighting, bokeh background, negative space, muted colors,
  desaturated palette, subtle accent color, quiet scene, stillness,
  melancholic, whimsical, poetic, surreal but restrained

  Support & Community 💛 If you enjoy Tiny Things , please consider giving the
  LoRA a 👍 thumbs up and posting your first generated image on the model
  page. Seeing how others use the style helps build momentum, spreads the
  buzz, and genuinely keeps me inspired to keep creating and refining new
  work. Every image shared makes a difference. I REALLY look forward to
  seeing what you create with it. (I know that I always say that... but this
  time I await with inner demon-child giggles waiting release)

───────────────────────────────────────────────────────────────────────────────
  VERSION NOTES
───────────────────────────────────────────────────────────────────────────────
  Version 1 of Qwen is why the others have new versions. It's stellar but
  really requires more dataset prep because (at least for me) it is punishing
  in the most interesting of ways when training.

───────────────────────────────────────────────────────────────────────────────
  EXAMPLE MEDIA
───────────────────────────────────────────────────────────────────────────────
  6 preview(s) in ./example_images/ — 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, 928x1664)
  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 01:00 UTC.
  Stats and description are the author's; pros/cons are derived from the
  evidence tagged beside each line.
───────────────────────────────────────────────────────────────────────────────