ludicrains/deep-gaze by Ciro Santilli 40 Updated 2025-07-16
This just works, but it is also so incredibly slow that it is useless (or at least the quality it reaches in the time we have patience to wait from), at least on any setup we've managed to try, including e.g. on an Nvidia A10G on a g5.xlarge. Running:
time imagine "a house in the forest"
would likely take hours to complete.
Conda install is a bit annoying, but gets the job done. The generation quality is very good.
Someone should package this better for end user "just works after Conda install" image generation, it is currently much more of a library setup.
First install Conda as per Section "Install Conda on Ubuntu", and then just follow the instructions from the README, notably the Reference sampling script section.
git clone https://github.com/runwayml/stable-diffusion
cd stable-diffusion/
git checkout 08ab4d326c96854026c4eb3454cd3b02109ee982
conda env create -f environment.yaml
conda activate ldm
mkdir -p models/ldm/stable-diffusion-v1/
wget -O models/ldm/stable-diffusion-v1/model.ckpt https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt
python scripts/txt2img.py --prompt "a photograph of an astronaut riding a horse" --plms
This took about 2 minutes and generated 6 images under outputs/txt2img-samples/samples, includining an image outputs/txt2img-samples/grid-0000.png which is a grid montage containing all the six images in one:
https://raw.githubusercontent.com/cirosantilli/media/master/Runwayml_stable-diffusion_a-photograph-of-an-astronaut-riding-a-horse.png
TODO how to change the number of images?
A quick attempt at removing their useless safety features (watermark and NSFW text filter) is:
diff --git a/scripts/txt2img.py b/scripts/txt2img.py
index 59c16a1..0b8ef25 100644
--- a/scripts/txt2img.py
+++ b/scripts/txt2img.py
@@ -87,10 +87,10 @@ def load_replacement(x):
 def check_safety(x_image):
     safety_checker_input = safety_feature_extractor(numpy_to_pil(x_image), return_tensors="pt")
     x_checked_image, has_nsfw_concept = safety_checker(images=x_image, clip_input=safety_checker_input.pixel_values)
-    assert x_checked_image.shape[0] == len(has_nsfw_concept)
-    for i in range(len(has_nsfw_concept)):
-        if has_nsfw_concept[i]:
-            x_checked_image[i] = load_replacement(x_checked_image[i])
+    #assert x_checked_image.shape[0] == len(has_nsfw_concept)
+    #for i in range(len(has_nsfw_concept)):
+    #    if has_nsfw_concept[i]:
+    #        x_checked_image[i] = load_replacement(x_checked_image[i])
     return x_checked_image, has_nsfw_concept


@@ -314,7 +314,7 @@ def main():
                             for x_sample in x_checked_image_torch:
                                 x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c')
                                 img = Image.fromarray(x_sample.astype(np.uint8))
-                                img = put_watermark(img, wm_encoder)
+                                # img = put_watermark(img, wm_encoder)
                                 img.save(os.path.join(sample_path, f"{base_count:05}.png"))
                                 base_count += 1
but that produced 4 black images and only two unfiltered ones. Also likely the lack of sexual training data makes its porn suck, and not in the good way.
Stanford Smallville by Ciro Santilli 40 Updated 2025-07-16
Published as: arxiv.org/pdf/2304.03442.pdf Generative Agents: Interactive Simulacra of Human Behavior by Park et al.
Video 1.
AI Agents Behaving Like Humans by Prompt Engineering (2023)
. Source.
Lysozyme by Ciro Santilli 40 Updated 2025-07-16
Breaks up peptidoglycan present in the bacterial cell wall, which is thicker in Gram-positive bacteria, which is what this enzyme seems to target.
Part of the inate immune system.
It is present on basically everything that mammals and birds excrete, and it kills bacteria, both of which are reasons why it was discovered relatively early on.
  • reconstruction/ecoli/flat/condition/nutrient/minimal.tsv contains the nutrients in a minimal environment in which the cell survives:
    "molecule id" "lower bound (units.mmol / units.g / units.h)" "upper bound (units.mmol / units.g / units.h)"
    "ADP[c]" 3.15 3.15
    "PI[c]" 3.15 3.15
    "PROTON[c]" 3.15 3.15
    "GLC[p]" NaN 20
    "OXYGEN-MOLECULE[p]" NaN NaN
    "AMMONIUM[c]" NaN NaN
    "PI[p]" NaN NaN
    "K+[p]" NaN NaN
    "SULFATE[p]" NaN NaN
    "FE+2[p]" NaN NaN
    "CA+2[p]" NaN NaN
    "CL-[p]" NaN NaN
    "CO+2[p]" NaN NaN
    "MG+2[p]" NaN NaN
    "MN+2[p]" NaN NaN
    "NI+2[p]" NaN NaN
    "ZN+2[p]" NaN NaN
    "WATER[p]" NaN NaN
    "CARBON-DIOXIDE[p]" NaN NaN
    "CPD0-1958[p]" NaN NaN
    "L-SELENOCYSTEINE[c]" NaN NaN
    "GLC-D-LACTONE[c]" NaN NaN
    "CYTOSINE[c]" NaN NaN
    If we compare that to reconstruction/ecoli/flat/condition/nutrient/minimal_plus_amino_acids.tsv, we see that it adds the 20 amino acids on top of the minimal condition:
    "L-ALPHA-ALANINE[p]" NaN NaN
    "ARG[p]" NaN NaN
    "ASN[p]" NaN NaN
    "L-ASPARTATE[p]" NaN NaN
    "CYS[p]" NaN NaN
    "GLT[p]" NaN NaN
    "GLN[p]" NaN NaN
    "GLY[p]" NaN NaN
    "HIS[p]" NaN NaN
    "ILE[p]" NaN NaN
    "LEU[p]" NaN NaN
    "LYS[p]" NaN NaN
    "MET[p]" NaN NaN
    "PHE[p]" NaN NaN
    "PRO[p]" NaN NaN
    "SER[p]" NaN NaN
    "THR[p]" NaN NaN
    "TRP[p]" NaN NaN
    "TYR[p]" NaN NaN
    "L-SELENOCYSTEINE[c]" NaN NaN
    "VAL[p]" NaN NaN
    so we guess that NaN in the upper mound likely means infinite.
    We can try to understand the less obvious ones:
    • ADP: TODO
    • PI: TODO
    • PROTON[c]: presumably a measure of pH
    • GLC[p]: glucose, this can be seen by comparing minimal.tsv with minimal_no_glucose.tsv
    • AMMONIUM: ammonium. This appears to be the primary source of nitrogen atoms for producing amino acids.
    • CYTOSINE[c]: hmmm, why is external cytosine needed? Weird.
  • reconstruction/ecoli/flat/reconstruction/ecoli/flat/condition/timeseries/ contains sequences of conditions for each time. For example:
    • reconstruction/ecoli/flat/reconstruction/ecoli/flat/condition/timeseries/000000_basal.tsv contains:
      "time (units.s)" "nutrients"
      0 "minimal"
      which means just using reconstruction/ecoli/flat/condition/nutrient/minimal.tsv until infinity. That is the default one used by runSim.py, as can be seen from ./out/manual/wildtype_000000/000000/generation_000000/000000/simOut/Environment/attributes/nutrientTimeSeriesLabel which contains just 000000_basal.
    • reconstruction/ecoli/flat/reconstruction/ecoli/flat/condition/timeseries/000001_cut_glucose.tsv is more interesting and contains:
      "time (units.s)" "nutrients"
      0 "minimal"
      1200 "minimal_no_glucose"
      so we see that this will shift the conditions half-way to a condition that will eventually kill the bacteria because it will run out of glucose and thus energy!
    Timeseries can be selected with --variant nutrientTimeSeries X Y, see also: run variants.
    We can use that variant with:
    VARIANT="condition" FIRST_VARIANT_INDEX=1 LAST_VARIANT_INDEX=1 python runscripts/manual/runSim.py
  • reconstruction/ecoli/flat/condition/condition_defs.tsv contains lines of form:
    "condition" "nutrients"                "genotype perturbations" "doubling time (units.min)" "active TFs"
    "basal"     "minimal"                  {}                       44.0                        []
    "no_oxygen" "minimal_minus_oxygen"     {}                       100.0                       []
    "with_aa"   "minimal_plus_amino_acids" {}                       25.0                        ["CPLX-125", "MONOMER0-162", "CPLX0-7671", "CPLX0-228", "MONOMER0-155"]
    • condition refers to entries in reconstruction/ecoli/flat/condition/condition_defs.tsv
    • nutrients refers to entries under reconstruction/ecoli/flat/condition/nutrient/, e.g. reconstruction/ecoli/flat/condition/nutrient/minimal.tsv or reconstruction/ecoli/flat/condition/nutrient/minimal_plus_amino_acids.tsv
    • genotype perturbations: there aren't any in the file, but this suggests that genotype modifications can also be incorporated here
    • doubling time: TODO experimental data? Because this should be a simulation output, right? Or do they cheat and fix doubling by time?
    • active TFs: this suggests that they are cheating transcription factors here, as those would ideally be functions of other more basic inputs

Pinned article: Introduction to the OurBigBook Project

Welcome to the OurBigBook Project! Our goal is to create the perfect publishing platform for STEM subjects, and get university-level students to write the best free STEM tutorials ever.
Everyone is welcome to create an account and play with the site: ourbigbook.com/go/register. We belive that students themselves can write amazing tutorials, but teachers are welcome too. You can write about anything you want, it doesn't have to be STEM or even educational. Silly test content is very welcome and you won't be penalized in any way. Just keep it legal!
We have two killer features:
  1. topics: topics group articles by different users with the same title, e.g. here is the topic for the "Fundamental Theorem of Calculus" ourbigbook.com/go/topic/fundamental-theorem-of-calculus
    Articles of different users are sorted by upvote within each article page. This feature is a bit like:
    • a Wikipedia where each user can have their own version of each article
    • a Q&A website like Stack Overflow, where multiple people can give their views on a given topic, and the best ones are sorted by upvote. Except you don't need to wait for someone to ask first, and any topic goes, no matter how narrow or broad
    This feature makes it possible for readers to find better explanations of any topic created by other writers. And it allows writers to create an explanation in a place that readers might actually find it.
    Figure 1.
    Screenshot of the "Derivative" topic page
    . View it live at: ourbigbook.com/go/topic/derivative
  2. local editing: you can store all your personal knowledge base content locally in a plaintext markup format that can be edited locally and published either:
    This way you can be sure that even if OurBigBook.com were to go down one day (which we have no plans to do as it is quite cheap to host!), your content will still be perfectly readable as a static site.
    Figure 2.
    You can publish local OurBigBook lightweight markup files to either https://OurBigBook.com or as a static website
    .
    Figure 3.
    Visual Studio Code extension installation
    .
    Figure 4.
    Visual Studio Code extension tree navigation
    .
    Figure 5.
    Web editor
    . You can also edit articles on the Web editor without installing anything locally.
    Video 3.
    Edit locally and publish demo
    . Source. This shows editing OurBigBook Markup and publishing it using the Visual Studio Code extension.
    Video 4.
    OurBigBook Visual Studio Code extension editing and navigation demo
    . Source.
  3. https://raw.githubusercontent.com/ourbigbook/ourbigbook-media/master/feature/x/hilbert-space-arrow.png
  4. Infinitely deep tables of contents:
    Figure 6.
    Dynamic article tree with infinitely deep table of contents
    .
    Descendant pages can also show up as toplevel e.g.: ourbigbook.com/cirosantilli/chordate-subclade
All our software is open source and hosted at: github.com/ourbigbook/ourbigbook
Further documentation can be found at: docs.ourbigbook.com
Feel free to reach our to us for any help or suggestions: docs.ourbigbook.com/#contact